add tgi2.4.0

Cargo.lock

@@ -4,9 +4,9 @@ version = 3
 
 [[package]]
 name = "addr2line"
-version = "0.22.0"
+version = "0.24.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6e4503c46a5c0c7844e948c9a4d6acd9f50cccb4de1c48eb9e291ea17470c678"
+checksum = "dfbe277e56a376000877090da837660b4427aad530e3028d44e0bffe4f89a1c1"
 dependencies = [
  "gimli",
 ]
@@ -17,6 +17,12 @@ version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f26201604c87b1e01bd3d98f8d5d9a8fcbb815e8cedb41ffccbeb4bf593a35fe"
 
+[[package]]
+name = "adler2"
+version = "2.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "512761e0bb2578dd7380c6baaa0f4ce03e84f95e960231d1dec8bf4d7d6e2627"
+
 [[package]]
 name = "ahash"
 version = "0.8.11"
@@ -46,11 +52,17 @@ version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4aa90d7ce82d4be67b64039a3d588d38dbcc6736577de4a847025ce5b0c468d1"
 
+[[package]]
+name = "allocator-api2"
+version = "0.2.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5c6cb57a04249c6480766f7f7cef5467412af1490f8d1e243141daddada3264f"
+
 [[package]]
 name = "anstream"
-version = "0.6.14"
+version = "0.6.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "418c75fa768af9c03be99d17643f93f79bbba589895012a80e3452a19ddda15b"
+checksum = "23a1e53f0f5d86382dafe1cf314783b2044280f406e7e1506368220ad11b1338"
 dependencies = [
  "anstyle",
  "anstyle-parse",
@@ -63,43 +75,43 @@ dependencies = [
 
 [[package]]
 name = "anstyle"
-version = "1.0.7"
+version = "1.0.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "038dfcf04a5feb68e9c60b21c9625a54c2c0616e79b72b0fd87075a056ae1d1b"
+checksum = "8365de52b16c035ff4fcafe0092ba9390540e3e352870ac09933bebcaa2c8c56"
 
 [[package]]
 name = "anstyle-parse"
-version = "0.2.4"
+version = "0.2.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c03a11a9034d92058ceb6ee011ce58af4a9bf61491aa7e1e59ecd24bd40d22d4"
+checksum = "3b2d16507662817a6a20a9ea92df6652ee4f94f914589377d69f3b21bc5798a9"
 dependencies = [
  "utf8parse",
 ]
 
 [[package]]
 name = "anstyle-query"
-version = "1.1.0"
+version = "1.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ad186efb764318d35165f1758e7dcef3b10628e26d41a44bc5550652e6804391"
+checksum = "79947af37f4177cfead1110013d678905c37501914fba0efea834c3fe9a8d60c"
 dependencies = [
- "windows-sys 0.52.0",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]
 name = "anstyle-wincon"
-version = "3.0.3"
+version = "3.0.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "61a38449feb7068f52bb06c12759005cf459ee52bb4adc1d5a7c4322d716fb19"
+checksum = "2109dbce0e72be3ec00bed26e6a7479ca384ad226efdd66db8fa2e3a38c83125"
 dependencies = [
  "anstyle",
- "windows-sys 0.52.0",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]
 name = "anyhow"
-version = "1.0.86"
+version = "1.0.91"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b3d1d046238990b9cf5bcde22a3fb3584ee5cf65fb2765f454ed428c7a0063da"
+checksum = "c042108f3ed77fd83760a5fd79b53be043192bb3b9dba91d8c574c0ada7850c8"
 
 [[package]]
 name = "arbitrary"
@@ -121,14 +133,14 @@ checksum = "0ae92a5119aa49cdbcf6b9f893fe4e1d98b04ccbf82ee0584ad948a44a734dea"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
 name = "arrayvec"
-version = "0.7.4"
+version = "0.7.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "96d30a06541fbafbc7f82ed10c06164cfbd2c401138f6addd8404629c4b16711"
+checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"
 
 [[package]]
 name = "async-rustls"
@@ -143,9 +155,9 @@ dependencies = [
 
 [[package]]
 name = "async-stream"
-version = "0.3.5"
+version = "0.3.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cd56dd203fef61ac097dd65721a419ddccb106b2d2b70ba60a6b529f03961a51"
+checksum = "0b5a71a6f37880a80d1d7f19efd781e4b5de42c88f0722cc13bcb6cc2cfe8476"
 dependencies = [
  "async-stream-impl",
  "futures-core",
@@ -154,24 +166,24 @@ dependencies = [
 
 [[package]]
 name = "async-stream-impl"
-version = "0.3.5"
+version = "0.3.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "16e62a023e7c117e27523144c5d2459f4397fcc3cab0085af8e2224f643a0193"
+checksum = "c7c24de15d275a1ecfd47a380fb4d5ec9bfe0933f309ed5e705b775596a3574d"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
 name = "async-trait"
-version = "0.1.80"
+version = "0.1.83"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c6fa2087f2753a7da8cc1c0dbfcf89579dd57458e36769de5ac750b4671737ca"
+checksum = "721cae7de5c34fbb2acd27e21e6d2cf7b886dce0c27388d46c4e6c47ea4318dd"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -180,11 +192,22 @@ version = "1.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1505bd5d3d116872e7271a6d4e16d81d0c8570876c8de68093a09ac269d8aac0"
 
+[[package]]
+name = "atty"
+version = "0.2.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d9b39be18770d11421cdb1b9947a45dd3f37e93092cbf377614828a319d5fee8"
+dependencies = [
+ "hermit-abi 0.1.19",
+ "libc",
+ "winapi",
+]
+
 [[package]]
 name = "autocfg"
-version = "1.3.0"
+version = "1.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0c4b4d0bd25bd0b74681c0ad21497610ce1b7c91b1022cd21c80c6fbdd9476b0"
+checksum = "ace50bade8e6234aa140d9a2f552bbee1db4d353f69b8217bc503490fc1a9f26"
 
 [[package]]
 name = "av1-grain"
@@ -213,9 +236,9 @@ dependencies = [
 
 [[package]]
 name = "avif-serialize"
-version = "0.8.1"
+version = "0.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "876c75a42f6364451a033496a14c44bffe41f5f4a8236f697391f11024e596d2"
+checksum = "e335041290c43101ca215eed6f43ec437eb5a42125573f600fc3fa42b9bddd62"
 dependencies = [
  "arrayvec",
 ]
@@ -234,9 +257,9 @@ dependencies = [
 
 [[package]]
 name = "aws-lc-rs"
-version = "1.7.3"
+version = "1.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bf7d844e282b4b56750b2d4e893b2205581ded8709fddd2b6aa5418c150ca877"
+checksum = "cdd82dba44d209fddb11c190e0a94b78651f95299598e472215667417a03ff1d"
 dependencies = [
  "aws-lc-sys",
  "mirai-annotations",
@@ -246,9 +269,9 @@ dependencies = [
 
 [[package]]
 name = "aws-lc-sys"
-version = "0.18.0"
+version = "0.22.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c3a2c29203f6bf296d01141cc8bb9dbd5ecd4c27843f2ee0767bcd5985a927da"
+checksum = "df7a4168111d7eb622a31b214057b8509c0a7e1794f44c546d742330dc793972"
 dependencies = [
  "bindgen",
  "cc",
@@ -272,7 +295,7 @@ dependencies = [
  "futures-util",
  "http 0.2.12",
  "http-body 0.4.6",
- "hyper 0.14.29",
+ "hyper 0.14.31",
  "itoa",
  "matchit",
  "memchr",
@@ -286,25 +309,25 @@ dependencies = [
  "serde_urlencoded",
  "sync_wrapper 0.1.2",
  "tokio",
- "tower",
+ "tower 0.4.13",
  "tower-layer",
  "tower-service",
 ]
 
 [[package]]
 name = "axum"
-version = "0.7.5"
+version = "0.7.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3a6c9af12842a67734c9a2e355436e5d03b22383ed60cf13cd0c18fbfe3dcbcf"
+checksum = "504e3947307ac8326a5437504c517c4b56716c9d98fac0028c2acc7ca47d70ae"
 dependencies = [
  "async-trait",
- "axum-core 0.4.3",
+ "axum-core 0.4.5",
  "bytes",
  "futures-util",
  "http 1.1.0",
- "http-body 1.0.0",
+ "http-body 1.0.1",
  "http-body-util",
- "hyper 1.3.1",
+ "hyper 1.5.0",
  "hyper-util",
  "itoa",
  "matchit",
@@ -319,7 +342,7 @@ dependencies = [
  "serde_urlencoded",
  "sync_wrapper 1.0.1",
  "tokio",
- "tower",
+ "tower 0.5.1",
  "tower-layer",
  "tower-service",
  "tracing",
@@ -344,20 +367,20 @@ dependencies = [
 
 [[package]]
 name = "axum-core"
-version = "0.4.3"
+version = "0.4.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a15c63fd72d41492dc4f497196f5da1fb04fb7529e631d73630d1b491e47a2e3"
+checksum = "09f2bd6146b97ae3359fa0cc6d6b376d9539582c7b4220f041a33ec24c226199"
 dependencies = [
  "async-trait",
  "bytes",
  "futures-util",
  "http 1.1.0",
- "http-body 1.0.0",
+ "http-body 1.0.1",
  "http-body-util",
  "mime",
  "pin-project-lite",
  "rustversion",
- "sync_wrapper 0.1.2",
+ "sync_wrapper 1.0.1",
  "tower-layer",
  "tower-service",
  "tracing",
@@ -369,13 +392,13 @@ version = "0.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bdad298231394729042d1f155b93f9fdf0b5ee1aea0b62404c4d7341f7d8fe08"
 dependencies = [
- "axum 0.7.5",
+ "axum 0.7.7",
  "futures-core",
  "futures-util",
  "http 1.1.0",
  "opentelemetry 0.21.0",
  "pin-project-lite",
- "tower",
+ "tower 0.4.13",
  "tracing",
  "tracing-opentelemetry 0.22.0",
  "tracing-opentelemetry-instrumentation-sdk",
@@ -383,17 +406,17 @@ dependencies = [
 
 [[package]]
 name = "backtrace"
-version = "0.3.73"
+version = "0.3.74"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5cc23269a4f8976d0a4d2e7109211a419fe30e8d88d677cd60b6bc79c5732e0a"
+checksum = "8d82cb332cdfaed17ae235a638438ac4d4839913cc2af585c3c6746e8f8bee1a"
 dependencies = [
  "addr2line",
- "cc",
  "cfg-if",
  "libc",
- "miniz_oxide",
+ "miniz_oxide 0.8.0",
  "object",
  "rustc-demangle",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -416,9 +439,9 @@ checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
 
 [[package]]
 name = "bindgen"
-version = "0.69.4"
+version = "0.69.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a00dc851838a2120612785d195287475a3ac45514741da670b735818822129a0"
+checksum = "271383c67ccabffb7381723dea0672a673f292304fcb45c01cc648c7a8d58088"
 dependencies = [
  "bitflags 2.6.0",
  "cexpr",
@@ -433,7 +456,7 @@ dependencies = [
  "regex",
  "rustc-hash",
  "shlex",
- "syn 2.0.68",
+ "syn 2.0.85",
  "which",
 ]
 
@@ -472,9 +495,9 @@ checksum = "b048fb63fd8b5923fc5aa7b340d8e156aec7ec02f0c78fa8a6ddc2613f6f71de"
 
 [[package]]
 name = "bitstream-io"
-version = "2.4.2"
+version = "2.5.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "415f8399438eb5e4b2f73ed3152a3448b98149dda642a957ee704e1daa5cf1d8"
+checksum = "b81e1519b0d82120d2fd469d5bfb2919a9361c48b02d82d04befc1cdd2002452"
 
 [[package]]
 name = "block-buffer"
@@ -487,9 +510,9 @@ dependencies = [
 
 [[package]]
 name = "built"
-version = "0.7.3"
+version = "0.7.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c6a6c0b39c38fd754ac338b00a88066436389c0f029da5d37d1e01091d9b7c17"
+checksum = "c360505aed52b7ec96a3636c3f039d99103c37d1d9b4f7a8c743d3ea9ffcd03b"
 
 [[package]]
 name = "bumpalo"
@@ -505,9 +528,9 @@ checksum = "5ce89b21cab1437276d2650d57e971f9d548a2d9037cc231abdc0562b97498ce"
 
 [[package]]
 name = "bytemuck"
-version = "1.16.1"
+version = "1.19.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b236fc92302c97ed75b38da1f4917b5cdda4984745740f153a5d3059e48d725e"
+checksum = "8334215b81e418a0a7bdb8ef0849474f40bb10c8b71f1c4ed315cff49f32494d"
 
 [[package]]
 name = "byteorder"
@@ -523,15 +546,15 @@ checksum = "8f1fe948ff07f4bd06c30984e69f5b4899c516a3ef74f34df92a2df2ab535495"
 
 [[package]]
 name = "bytes"
-version = "1.6.0"
+version = "1.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "514de17de45fdb8dc022b1a7975556c53c86f9f0aa5f534b98977b171857c2c9"
+checksum = "9ac0150caa2ae65ca5bd83f25c7de183dea78d4d366469f148435e2acfbad0da"
 
 [[package]]
 name = "camino"
-version = "1.1.7"
+version = "1.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e0ec6b951b160caa93cc0c7b209e5a3bff7aae9062213451ac99493cd844c239"
+checksum = "8b96ec4966b5813e2c0507c1f86115c8c5abaadc3980879c3424042a02fd1ad3"
 dependencies = [
  "serde",
 ]
@@ -565,15 +588,30 @@ version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "df8670b8c7b9dae1793364eafadf7239c40d669904660c5960d74cfd80b46a53"
 
+[[package]]
+name = "cast"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "37b2a672a2cb129a2e41c10b1224bb368f9f37a2b16b612598138befd7b37eb5"
+
+[[package]]
+name = "castaway"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0abae9be0aaf9ea96a3b1b8b1b55c602ca751eba1b1500220cea4ecbafe7c0d5"
+dependencies = [
+ "rustversion",
+]
+
 [[package]]
 name = "cc"
-version = "1.0.101"
+version = "1.1.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ac367972e516d45567c7eafc73d24e1c193dcf200a8d94e9db7b3d38b349572d"
+checksum = "c2e7962b54006dcfcc61cb72735f4d89bb97061dd6a7ed882ec6b8ee53714c6f"
 dependencies = [
  "jobserver",
  "libc",
- "once_cell",
+ "shlex",
 ]
 
 [[package]]
@@ -607,6 +645,12 @@ version = "0.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fd16c4719339c4530435d38e511904438d07cce7950afa3718a84ac36c10e89e"
 
+[[package]]
+name = "cfg_aliases"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
+
 [[package]]
 name = "clang-sys"
 version = "1.8.1"
@@ -620,9 +664,20 @@ dependencies = [
 
 [[package]]
 name = "clap"
-version = "4.5.7"
+version = "2.34.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a0610544180c38b88101fecf2dd634b174a62eef6946f84dfc6a7127512b381c"
+dependencies = [
+ "bitflags 1.3.2",
+ "textwrap",
+ "unicode-width",
+]
+
+[[package]]
+name = "clap"
+version = "4.5.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5db83dced34638ad474f39f250d7fea9598bdd239eaced1bdf45d597da0f433f"
+checksum = "b97f376d85a664d5837dbae44bf546e6477a679ff6610010f17276f686d867e8"
 dependencies = [
  "clap_builder",
  "clap_derive",
@@ -630,9 +685,9 @@ dependencies = [
 
 [[package]]
 name = "clap_builder"
-version = "4.5.7"
+version = "4.5.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f7e204572485eb3fbf28f871612191521df159bc3e15a9f5064c66dba3a8c05f"
+checksum = "19bc80abd44e4bed93ca373a0704ccbd1b710dc5749406201bb018272808dc54"
 dependencies = [
  "anstream",
  "anstyle",
@@ -642,31 +697,41 @@ dependencies = [
 
 [[package]]
 name = "clap_derive"
-version = "4.5.5"
+version = "4.5.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c780290ccf4fb26629baa7a1081e68ced113f1d3ec302fa5948f1c381ebf06c6"
+checksum = "4ac6a0c7b1a9e9a5186361f67dfa1b88213572f427fb9ab038efb2bd8c582dab"
 dependencies = [
  "heck 0.5.0",
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
 name = "clap_lex"
-version = "0.7.1"
+version = "0.7.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4b82cf0babdbd58558212896d1a4272303a57bdb245c2bf1147185fb45640e70"
+checksum = "1462739cb27611015575c0c11df5df7601141071f07518d56fcc1be504cbec97"
 
 [[package]]
 name = "cmake"
-version = "0.1.50"
+version = "0.1.51"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a31c789563b815f77f4250caee12365734369f942439b7defd71e18a48197130"
+checksum = "fb1e43aa7fd152b1f968787f7dbcdeb306d1867ff373c69955211876c053f91a"
 dependencies = [
  "cc",
 ]
 
+[[package]]
+name = "codespan-reporting"
+version = "0.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3538270d33cc669650c4b093848450d380def10c331d38c768e34cac80576e6e"
+dependencies = [
+ "termcolor",
+ "unicode-width",
+]
+
 [[package]]
 name = "color_quant"
 version = "1.1.0"
@@ -675,9 +740,23 @@ checksum = "3d7b894f5411737b7867f4827955924d7c254fc9f4d91a6aad6b097804b1018b"
 
 [[package]]
 name = "colorchoice"
-version = "1.0.1"
+version = "1.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b6a852b24ab71dffc585bcb46eaf7959d175cb865a7152e35b348d1b2960422"
+checksum = "5b63caa9aa9397e2d9480a9b13673856c78d8ac123288526c37d7839f2a86990"
+
+[[package]]
+name = "compact_str"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6050c3a16ddab2e412160b31f2c871015704239bca62f72f6e5f0be631d3f644"
+dependencies = [
+ "castaway",
+ "cfg-if",
+ "itoa",
+ "rustversion",
+ "ryu",
+ "static_assertions",
+]
 
 [[package]]
 name = "console"
@@ -704,15 +783,15 @@ dependencies = [
 
 [[package]]
 name = "core-foundation-sys"
-version = "0.8.6"
+version = "0.8.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "06ea2b9bc92be3c2baa9334a323ebca2d6f074ff852cd1d7b11064035cd3868f"
+checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
 
 [[package]]
 name = "cpufeatures"
-version = "0.2.12"
+version = "0.2.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "53fe5e26ff1b7aef8bca9c6080520cfb8d9333c7568e1829cef191a9723e5504"
+checksum = "608697df725056feaccfa42cffdaeeec3fccc4ffc38358ecd19b243e716a78e0"
 dependencies = [
  "libc",
 ]
@@ -726,6 +805,42 @@ dependencies = [
  "cfg-if",
 ]
 
+[[package]]
+name = "criterion"
+version = "0.3.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b01d6de93b2b6c65e17c634a26653a29d107b3c98c607c765bf38d041531cd8f"
+dependencies = [
+ "atty",
+ "cast",
+ "clap 2.34.0",
+ "criterion-plot",
+ "csv",
+ "itertools 0.10.5",
+ "lazy_static",
+ "num-traits",
+ "oorandom",
+ "plotters",
+ "rayon",
+ "regex",
+ "serde",
+ "serde_cbor",
+ "serde_derive",
+ "serde_json",
+ "tinytemplate",
+ "walkdir",
+]
+
+[[package]]
+name = "criterion-plot"
+version = "0.4.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2673cc8207403546f45f5fd319a974b1e6983ad1a3ee7e6041650013be041876"
+dependencies = [
+ "cast",
+ "itertools 0.10.5",
+]
+
 [[package]]
 name = "crossbeam-channel"
 version = "0.5.13"
@@ -762,15 +877,15 @@ checksum = "22ec99545bb0ed0ea7bb9b8e1e9122ea386ff8a48c0922e43f36d45ab09e0e80"
 
 [[package]]
 name = "crossterm"
-version = "0.27.0"
+version = "0.28.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f476fe445d41c9e991fd07515a6f463074b782242ccf4a5b7b1d1012e70824df"
+checksum = "829d955a0bb380ef178a640b91779e3987da38c9aea133b20614cfed8cdea9c6"
 dependencies = [
  "bitflags 2.6.0",
  "crossterm_winapi",
- "libc",
  "mio",
  "parking_lot",
+ "rustix",
  "signal-hook",
  "signal-hook-mio",
  "winapi",
@@ -801,21 +916,86 @@ dependencies = [
  "typenum",
 ]
 
+[[package]]
+name = "csv"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac574ff4d437a7b5ad237ef331c17ccca63c46479e5b5453eb8e10bb99a759fe"
+dependencies = [
+ "csv-core",
+ "itoa",
+ "ryu",
+ "serde",
+]
+
+[[package]]
+name = "csv-core"
+version = "0.1.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5efa2b3d7902f4b634a20cae3c9c4e6209dc4779feb6863329607560143efa70"
+dependencies = [
+ "memchr",
+]
+
 [[package]]
 name = "ctrlc"
-version = "3.4.4"
+version = "3.4.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "672465ae37dc1bc6380a6547a8883d5dd397b0f1faaad4f265726cc7042a5345"
+checksum = "90eeab0aa92f3f9b4e87f258c72b139c207d251f9cbc1080a0086b86a8870dd3"
 dependencies = [
- "nix",
- "windows-sys 0.52.0",
+ "nix 0.29.0",
+ "windows-sys 0.59.0",
+]
+
+[[package]]
+name = "cxx"
+version = "1.0.129"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cbdc8cca144dce1c4981b5c9ab748761619979e515c3d53b5df385c677d1d007"
+dependencies = [
+ "cc",
+ "cxxbridge-flags",
+ "cxxbridge-macro",
+ "link-cplusplus",
+]
+
+[[package]]
+name = "cxx-build"
+version = "1.0.129"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c5764c3142ab44fcf857101d12c0ddf09c34499900557c764f5ad0597159d1fc"
+dependencies = [
+ "cc",
+ "codespan-reporting",
+ "once_cell",
+ "proc-macro2",
+ "quote",
+ "scratch",
+ "syn 2.0.85",
+]
+
+[[package]]
+name = "cxxbridge-flags"
+version = "1.0.129"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d422aff542b4fa28c2ce8e5cc202d42dbf24702345c1fba3087b2d3f8a1b90ff"
+
+[[package]]
+name = "cxxbridge-macro"
+version = "1.0.129"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a1719100f31492cd6adeeab9a0f46cdbc846e615fdb66d7b398aa46ec7fdd06f"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.85",
 ]
 
 [[package]]
 name = "darling"
-version = "0.20.9"
+version = "0.20.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "83b2eb4d90d12bdda5ed17de686c2acb4c57914f8f921b8da7e112b5a36f3fe1"
+checksum = "6f63b86c8a8826a49b8c21f08a2d07338eec8d900540f8630dc76284be802989"
 dependencies = [
  "darling_core",
  "darling_macro",
@@ -823,27 +1003,27 @@ dependencies = [
 
 [[package]]
 name = "darling_core"
-version = "0.20.9"
+version = "0.20.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "622687fe0bac72a04e5599029151f5796111b90f1baaa9b544d807a5e31cd120"
+checksum = "95133861a8032aaea082871032f5815eb9e98cef03fa916ab4500513994df9e5"
 dependencies = [
  "fnv",
  "ident_case",
  "proc-macro2",
  "quote",
  "strsim",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
 name = "darling_macro"
-version = "0.20.9"
+version = "0.20.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "733cabb43482b1a1b53eee8583c2b9e8684d592215ea83efd305dd31bc2f0178"
+checksum = "d336a2a514f6ccccaa3e09b02d41d35330c07ddf03a62165fcec10bb561c7806"
 dependencies = [
  "darling_core",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -857,33 +1037,33 @@ dependencies = [
 
 [[package]]
 name = "derive_builder"
-version = "0.20.0"
+version = "0.20.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0350b5cb0331628a5916d6c5c0b72e97393b8b6b03b47a9284f4e7f5a405ffd7"
+checksum = "507dfb09ea8b7fa618fcf76e953f4f5e192547945816d5358edffe39f6f94947"
 dependencies = [
  "derive_builder_macro",
 ]
 
 [[package]]
 name = "derive_builder_core"
-version = "0.20.0"
+version = "0.20.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d48cda787f839151732d396ac69e3473923d54312c070ee21e9effcaa8ca0b1d"
+checksum = "2d5bcf7b024d6835cfb3d473887cd966994907effbe9227e8c8219824d06c4e8"
 dependencies = [
  "darling",
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
 name = "derive_builder_macro"
-version = "0.20.0"
+version = "0.20.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "206868b8242f27cecce124c19fd88157fbd0dd334df2587f36417bafbc85097b"
+checksum = "ab63b0e2bf4d5928aff72e83a7dace85d7bba5fe12dcc3c5a572d78caffd3f3c"
 dependencies = [
  "derive_builder_core",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -919,9 +1099,9 @@ dependencies = [
 
 [[package]]
 name = "dunce"
-version = "1.0.4"
+version = "1.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "56ce8c6da7551ec6c462cbaf3bfbc75131ebbfa1c944aeaa9dab51ca1c5f0c3b"
+checksum = "92773504d58c093f6de2459af4af33faa518c13451eb8f2b5698ed3d36e7c813"
 
 [[package]]
 name = "easy-cast"
@@ -946,9 +1126,9 @@ checksum = "a357d28ed41a50f9c765dbfe56cbc04a64e53e5fc58ba79fbc34c10ef3df831f"
 
 [[package]]
 name = "encoding_rs"
-version = "0.8.34"
+version = "0.8.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b45de904aa0b010bce2ab45264d0631681847fa7b6f2eaa7dab7619943bc4f59"
+checksum = "75030f3c4f45dafd7586dd6780965a8c7e8e285a5ecb86713e63a79c5b2766f3"
 dependencies = [
  "cfg-if",
 ]
@@ -986,9 +1166,9 @@ checksum = "887d93f60543e9a9362ef8a21beedd0a833c5d9610e18c67abe15a5963dcb1a4"
 dependencies = [
  "bit_field",
  "flume",
- "half",
+ "half 2.4.1",
  "lebe",
- "miniz_oxide",
+ "miniz_oxide 0.7.4",
  "rayon-core",
  "smallvec",
  "zune-inflate",
@@ -1006,15 +1186,15 @@ dependencies = [
 
 [[package]]
 name = "fastrand"
-version = "2.1.0"
+version = "2.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9fc0510504f03c51ada170672ac806f1f105a88aa97a5281117e1ddc3368e51a"
+checksum = "e8c02a5121d4ea3eb16a80748c74f5549a5665e4c21333c6098f283870fbdea6"
 
 [[package]]
 name = "fdeflate"
-version = "0.3.4"
+version = "0.3.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4f9bfee30e4dedf0ab8b422f03af778d9612b63f502710fc500a334ebe2de645"
+checksum = "d8090f921a24b04994d9929e204f50b498a33ea6ba559ffaa05e04f7ee7fb5ab"
 dependencies = [
  "simd-adler32",
 ]
@@ -1027,12 +1207,12 @@ checksum = "0ce7134b9999ecaf8bcd65542e436736ef32ddca1b3e06094cb6ec5755203b80"
 
 [[package]]
 name = "flate2"
-version = "1.0.30"
+version = "1.0.34"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5f54427cfd1c7829e2a139fcefea601bf088ebca651d2bf53ebc600eac295dae"
+checksum = "a1b589b4dc103969ad3cf85c950899926ec64300a1a46d76c03a6072957036f0"
 dependencies = [
  "crc32fast",
- "miniz_oxide",
+ "miniz_oxide 0.8.0",
 ]
 
 [[package]]
@@ -1049,9 +1229,9 @@ checksum = "28a80e3145d8ad11ba0995949bbcf48b9df2be62772b3d351ef017dff6ecb853"
 
 [[package]]
 name = "flume"
-version = "0.11.0"
+version = "0.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "55ac459de2512911e4b674ce33cf20befaba382d05b62b008afc1c8b57cbf181"
+checksum = "da0e4dd2a88388a1f4ccc7c9ce104604dab68d9f408dc34cd45823d5a9069095"
 dependencies = [
  "spin 0.9.8",
 ]
@@ -1062,6 +1242,12 @@ version = "1.0.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
 
+[[package]]
+name = "foldhash"
+version = "0.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f81ec6369c545a7d40e4589b5597581fa1c441fe1cce96dd1de43159910a36a2"
+
 [[package]]
 name = "foreign-types"
 version = "0.3.2"
@@ -1104,9 +1290,9 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
 [[package]]
 name = "futures"
-version = "0.3.30"
+version = "0.3.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "645c6916888f6cb6350d2550b80fb63e734897a8498abe35cfb732b6487804b0"
+checksum = "65bc07b1a8bc7c85c5f2e110c476c7389b4554ba72af57d8445ea63a576b0876"
 dependencies = [
  "futures-channel",
  "futures-core",
@@ -1119,9 +1305,9 @@ dependencies = [
 
 [[package]]
 name = "futures-channel"
-version = "0.3.30"
+version = "0.3.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eac8f7d7865dcb88bd4373ab671c8cf4508703796caa2b1985a9ca867b3fcb78"
+checksum = "2dff15bf788c671c1934e366d07e30c1814a8ef514e1af724a602e8a2fbe1b10"
 dependencies = [
  "futures-core",
  "futures-sink",
@@ -1129,15 +1315,15 @@ dependencies = [
 
 [[package]]
 name = "futures-core"
-version = "0.3.30"
+version = "0.3.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dfc6580bb841c5a68e9ef15c77ccc837b40a7504914d52e47b8b0e9bbda25a1d"
+checksum = "05f29059c0c2090612e8d742178b0580d2dc940c837851ad723096f87af6663e"
 
 [[package]]
 name = "futures-executor"
-version = "0.3.30"
+version = "0.3.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a576fc72ae164fca6b9db127eaa9a9dda0d61316034f33a0a0d4eda41f02b01d"
+checksum = "1e28d1d997f585e54aebc3f97d39e72338912123a67330d723fdbb564d646c9f"
 dependencies = [
  "futures-core",
  "futures-task",
@@ -1146,38 +1332,38 @@ dependencies = [
 
 [[package]]
 name = "futures-io"
-version = "0.3.30"
+version = "0.3.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a44623e20b9681a318efdd71c299b6b222ed6f231972bfe2f224ebad6311f0c1"
+checksum = "9e5c1b78ca4aae1ac06c48a526a655760685149f0d465d21f37abfe57ce075c6"
 
 [[package]]
 name = "futures-macro"
-version = "0.3.30"
+version = "0.3.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "87750cf4b7a4c0625b1529e4c543c2182106e4dedc60a2a6455e00d212c489ac"
+checksum = "162ee34ebcb7c64a8abebc059ce0fee27c2262618d7b60ed8faf72fef13c3650"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
 name = "futures-sink"
-version = "0.3.30"
+version = "0.3.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9fb8e00e87438d937621c1c6269e53f536c14d3fbd6a042bb24879e57d474fb5"
+checksum = "e575fab7d1e0dcb8d0c7bcf9a63ee213816ab51902e6d244a95819acacf1d4f7"
 
 [[package]]
 name = "futures-task"
-version = "0.3.30"
+version = "0.3.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38d84fa142264698cdce1a9f9172cf383a0c82de1bddcf3092901442c4097004"
+checksum = "f90f7dce0722e95104fcb095585910c0977252f286e354b5e3bd38902cd99988"
 
 [[package]]
 name = "futures-util"
-version = "0.3.30"
+version = "0.3.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3d6401deb83407ab3da39eba7e33987a73c3df0c82b4bb5813ee871c19c41d48"
+checksum = "9fa08315bb612088cc391249efdc3bc77536f16c91f6cf495e6fbe85b20a4a81"
 dependencies = [
  "futures-channel",
  "futures-core",
@@ -1235,9 +1421,9 @@ dependencies = [
 
 [[package]]
 name = "gimli"
-version = "0.29.0"
+version = "0.31.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "40ecd4077b5ae9fd2e9e169b102c6c330d0605168eb0e8bf79952b256dbefffd"
+checksum = "07e28edb80900c19c28f1072f2e8aeca7fa06b23cd4169cefe1af5aa3260783f"
 
 [[package]]
 name = "glob"
@@ -1267,7 +1453,7 @@ dependencies = [
  "futures-sink",
  "futures-util",
  "http 0.2.12",
- "indexmap 2.2.6",
+ "indexmap 2.6.0",
  "slab",
  "tokio",
  "tokio-util",
@@ -1276,9 +1462,9 @@ dependencies = [
 
 [[package]]
 name = "h2"
-version = "0.4.5"
+version = "0.4.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fa82e28a107a8cc405f0839610bdc9b15f1e25ec7d696aa5cf173edbcb1486ab"
+checksum = "524e8ac6999421f49a846c2d4411f337e53497d8ec55d67753beffa43c5d9205"
 dependencies = [
  "atomic-waker",
  "bytes",
@@ -1286,13 +1472,19 @@ dependencies = [
  "futures-core",
  "futures-sink",
  "http 1.1.0",
- "indexmap 2.2.6",
+ "indexmap 2.6.0",
  "slab",
  "tokio",
  "tokio-util",
  "tracing",
 ]
 
+[[package]]
+name = "half"
+version = "1.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1b43ede17f21864e81be2fa654110bf1e793774238d86ef8555c37e6519c0403"
+
 [[package]]
 name = "half"
 version = "2.4.1"
@@ -1316,6 +1508,18 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e5274423e17b7c9fc20b6e7e208532f9b19825d82dfd615708b70edd83df41f1"
 dependencies = [
  "ahash",
+ "allocator-api2",
+]
+
+[[package]]
+name = "hashbrown"
+version = "0.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e087f84d4f86bf4b218b927129862374b72199ae7d8657835f1e89000eea4fb"
+dependencies = [
+ "allocator-api2",
+ "equivalent",
+ "foldhash",
 ]
 
 [[package]]
@@ -1330,6 +1534,15 @@ version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
 
+[[package]]
+name = "hermit-abi"
+version = "0.1.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "62b467343b94ba476dcb2500d242dadbb39557df889310ac77c5d99100aaac33"
+dependencies = [
+ "libc",
+]
+
 [[package]]
 name = "hermit-abi"
 version = "0.3.9"
@@ -1412,9 +1625,9 @@ dependencies = [
 
 [[package]]
 name = "http-body"
-version = "1.0.0"
+version = "1.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1cac85db508abc24a2e48553ba12a996e87244a0395ce011e62b37158745d643"
+checksum = "1efedce1fb8e6913f23e0c92de8e62cd5b772a67e7b3946df930a62566c93184"
 dependencies = [
  "bytes",
  "http 1.1.0",
@@ -1429,15 +1642,15 @@ dependencies = [
  "bytes",
  "futures-util",
  "http 1.1.0",
- "http-body 1.0.0",
+ "http-body 1.0.1",
  "pin-project-lite",
 ]
 
 [[package]]
 name = "httparse"
-version = "1.9.4"
+version = "1.9.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0fcc0b4a115bf80b728eb8ea024ad5bd707b615bfed49e0665b6e0f86fd082d9"
+checksum = "7d71d3574edd2771538b901e6549113b4006ece66150fb69c0fb6d9a2adae946"
 
 [[package]]
 name = "httpdate"
@@ -1447,9 +1660,9 @@ checksum = "df3b46402a9d5adb4c86a0cf463f42e19994e3ee891101b1841f30a545cb49a9"
 
 [[package]]
 name = "hyper"
-version = "0.14.29"
+version = "0.14.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f361cde2f109281a220d4307746cdfd5ee3f410da58a70377762396775634b33"
+checksum = "8c08302e8fa335b151b788c775ff56e7a03ae64ff85c548ee820fecb70356e85"
 dependencies = [
  "bytes",
  "futures-channel",
@@ -1471,16 +1684,16 @@ dependencies = [
 
 [[package]]
 name = "hyper"
-version = "1.3.1"
+version = "1.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fe575dd17d0862a9a33781c8c4696a55c320909004a67a00fb286ba8b1bc496d"
+checksum = "bbbff0a806a4728c99295b254c8838933b5b082d75e3cb70c8dab21fdfbcfa9a"
 dependencies = [
  "bytes",
  "futures-channel",
  "futures-util",
- "h2 0.4.5",
+ "h2 0.4.6",
  "http 1.1.0",
- "http-body 1.0.0",
+ "http-body 1.0.1",
  "httparse",
  "httpdate",
  "itoa",
@@ -1492,16 +1705,16 @@ dependencies = [
 
 [[package]]
 name = "hyper-rustls"
-version = "0.27.2"
+version = "0.27.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5ee4be2c948921a1a5320b629c4193916ed787a7f7f293fd3f7f5a6c9de74155"
+checksum = "08afdbb5c31130e3034af566421053ab03787c640246a446327f550d11bcb333"
 dependencies = [
  "futures-util",
  "http 1.1.0",
- "hyper 1.3.1",
+ "hyper 1.5.0",
  "hyper-util",
  "log",
- "rustls 0.23.10",
+ "rustls 0.23.15",
  "rustls-native-certs",
  "rustls-pki-types",
  "tokio",
@@ -1515,7 +1728,7 @@ version = "0.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bbb958482e8c7be4bc3cf272a766a2b0bf1a6755e7a6ae777f017a31d11b13b1"
 dependencies = [
- "hyper 0.14.29",
+ "hyper 0.14.31",
  "pin-project-lite",
  "tokio",
  "tokio-io-timeout",
@@ -1528,7 +1741,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d6183ddfa99b85da61a140bea0efc93fdf56ceaa041b37d553518030827f9905"
 dependencies = [
  "bytes",
- "hyper 0.14.29",
+ "hyper 0.14.31",
  "native-tls",
  "tokio",
  "tokio-native-tls",
@@ -1536,20 +1749,19 @@ dependencies = [
 
 [[package]]
 name = "hyper-util"
-version = "0.1.5"
+version = "0.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7b875924a60b96e5d7b9ae7b066540b1dd1cbd90d1828f54c92e02a283351c56"
+checksum = "41296eb09f183ac68eec06e03cdbea2e759633d4067b2f6552fc2e009bcad08b"
 dependencies = [
  "bytes",
  "futures-channel",
  "futures-util",
  "http 1.1.0",
- "http-body 1.0.0",
- "hyper 1.3.1",
+ "http-body 1.0.1",
+ "hyper 1.5.0",
  "pin-project-lite",
  "socket2",
  "tokio",
- "tower",
  "tower-service",
  "tracing",
 ]
@@ -1572,12 +1784,12 @@ dependencies = [
 
 [[package]]
 name = "image"
-version = "0.25.1"
+version = "0.25.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fd54d660e773627692c524beaad361aca785a4f9f5730ce91f42aabe5bce3d11"
+checksum = "bc144d44a31d753b02ce64093d532f55ff8dc4ebf2ffb8a63c0dda691385acae"
 dependencies = [
  "bytemuck",
- "byteorder",
+ "byteorder-lite",
  "color_quant",
  "exr",
  "gif",
@@ -1595,19 +1807,19 @@ dependencies = [
 
 [[package]]
 name = "image-webp"
-version = "0.1.2"
+version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d730b085583c4d789dfd07fdcf185be59501666a90c97c40162b37e4fdad272d"
+checksum = "e031e8e3d94711a9ccb5d6ea357439ef3dcbed361798bd4071dc4d9793fbe22f"
 dependencies = [
  "byteorder-lite",
- "thiserror",
+ "quick-error",
 ]
 
 [[package]]
 name = "imgref"
-version = "1.10.1"
+version = "1.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "44feda355f4159a7c757171a77de25daf6411e217b4cabd03bd6650690468126"
+checksum = "d0263a3d970d5c054ed9312c0057b4f3bde9c0b33836d3637361d4a9e6e7a408"
 
 [[package]]
 name = "indexmap"
@@ -1621,12 +1833,12 @@ dependencies = [
 
 [[package]]
 name = "indexmap"
-version = "2.2.6"
+version = "2.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "168fb715dda47215e360912c096649d23d58bf392ac62f73919e831745e40f26"
+checksum = "707907fe3c25f5424cce2cb7e1cbcafee6bdbe735ca90ef77c29e84591e5b9da"
 dependencies = [
  "equivalent",
- "hashbrown 0.14.5",
+ "hashbrown 0.15.0",
  "serde",
 ]
 
@@ -1662,6 +1874,16 @@ dependencies = [
  "tracing-opentelemetry 0.21.0",
 ]
 
+[[package]]
+name = "instability"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b23a0c8dfe501baac4adf6ebbfa6eddf8f0c07f56b058cc1288017e32397846c"
+dependencies = [
+ "quote",
+ "syn 2.0.85",
+]
+
 [[package]]
 name = "instant"
 version = "0.1.13"
@@ -1679,20 +1901,20 @@ checksum = "c34819042dc3d3971c46c2190835914dfbe0c3c13f61449b2997f4e9722dfa60"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
 name = "ipnet"
-version = "2.9.0"
+version = "2.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8f518f335dce6725a761382244631d86cf0ccb2863413590b31338feb467f9c3"
+checksum = "ddc24109865250148c2e0f3d25d4f0f479571723792d3802153c60922a4fb708"
 
 [[package]]
 name = "is_terminal_polyfill"
-version = "1.70.0"
+version = "1.70.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f8478577c03552c21db0e2724ffb8986a5ce7af88107e6be5d2ee6e158c12800"
+checksum = "7943c866cc5cd64cbc25b2e01621d07fa8eb2a1a23160ee81ce38704e97b8ecf"
 
 [[package]]
 name = "iso8601"
@@ -1730,6 +1952,15 @@ dependencies = [
  "either",
 ]
 
+[[package]]
+name = "itertools"
+version = "0.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "413ee7dfc52ee1a4949ceeb7dbc8a33f2d6c088194d9f922fb8318faf1f01186"
+dependencies = [
+ "either",
+]
+
 [[package]]
 name = "itoa"
 version = "1.0.11"
@@ -1738,9 +1969,9 @@ checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b"
 
 [[package]]
 name = "jobserver"
-version = "0.1.31"
+version = "0.1.32"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d2b099aaa34a9751c5bf0878add70444e1ed2dd73f347be99003d4577277de6e"
+checksum = "48d1dbcbbeb6a7fec7e059840aa538bd62aaccf972c7346c4d9d2059312853d0"
 dependencies = [
  "libc",
 ]
@@ -1753,9 +1984,9 @@ checksum = "f5d4a7da358eff58addd2877a45865158f0d78c911d43a5784ceb7bbf52833b0"
 
 [[package]]
 name = "js-sys"
-version = "0.3.69"
+version = "0.3.72"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "29c15563dc2726973df627357ce0c9ddddbea194836909d655df6a75d2cf296d"
+checksum = "6a88f1bda2bd75b0452a14784937d796722fdebfe50df998aeb3f0b7603019a9"
 dependencies = [
  "wasm-bindgen",
 ]
@@ -1770,7 +2001,7 @@ dependencies = [
  "anyhow",
  "base64 0.21.7",
  "bytecount",
- "clap",
+ "clap 4.5.20",
  "fancy-regex",
  "fraction",
  "getrandom",
@@ -1810,9 +2041,9 @@ checksum = "03087c2bad5e1034e8cace5926dec053fb3790248370865f5117a7d0213354c8"
 
 [[package]]
 name = "libc"
-version = "0.2.155"
+version = "0.2.161"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "97b3888a4aecf77e811145cadf6eef5901f4782c53886191b2f693f24761847c"
+checksum = "8e9489c2807c139ffd9c1794f4af0ebe86a828db53ecdc7fea2111d0fed085d1"
 
 [[package]]
 name = "libfuzzer-sys"
@@ -1827,12 +2058,12 @@ dependencies = [
 
 [[package]]
 name = "libloading"
-version = "0.8.4"
+version = "0.8.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e310b3a6b5907f99202fcdb4960ff45b93735d7c7d96b760fcff8db2dc0e103d"
+checksum = "4979f22fdb869068da03c9f7528f8297c6fd2606bc3a4affe42e6a823fdb8da4"
 dependencies = [
  "cfg-if",
- "windows-targets 0.52.5",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -1851,6 +2082,15 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "link-cplusplus"
+version = "1.0.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9d240c6f7e1ba3a28b0249f774e6a9dd0175054b52dfbb61b16eb8505c3785c9"
+dependencies = [
+ "cc",
+]
+
 [[package]]
 name = "linux-raw-sys"
 version = "0.4.14"
@@ -1869,9 +2109,9 @@ dependencies = [
 
 [[package]]
 name = "log"
-version = "0.4.21"
+version = "0.4.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "90ed8c1e510134f979dbc4f070f87d4313098b704861a105fe34231c70a3901c"
+checksum = "a7a70ba024b9dc04c27ea2f0c0548feb474ec5c54bba33a7f72f873a39d07b24"
 
 [[package]]
 name = "loop9"
@@ -1882,6 +2122,15 @@ dependencies = [
  "imgref",
 ]
 
+[[package]]
+name = "lru"
+version = "0.12.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "234cf4f4a04dc1f57e24b96cc0cd600cf2af460d4161ac5ecdd0af8e1f3b2a38"
+dependencies = [
+ "hashbrown 0.15.0",
+]
+
 [[package]]
 name = "macro_rules_attribute"
 version = "0.2.0"
@@ -1926,7 +2175,6 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8ea1f30cedd69f0a2954655f7188c6a834246d2bcf1e315e2ac40c4b24dc9519"
 dependencies = [
  "cfg-if",
- "rayon",
 ]
 
 [[package]]
@@ -1936,14 +2184,12 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3"
 
 [[package]]
-name = "metrics"
-version = "0.21.1"
+name = "memoffset"
+version = "0.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fde3af1a009ed76a778cb84fdef9e7dbbdf5775ae3e4cc1f434a6a307f6f76c5"
+checksum = "488016bfae457b036d996092f6cb448677611ce4449e970ceaf42695203f218a"
 dependencies = [
- "ahash",
- "metrics-macros",
- "portable-atomic",
+ "autocfg",
 ]
 
 [[package]]
@@ -1958,18 +2204,18 @@ dependencies = [
 
 [[package]]
 name = "metrics-exporter-prometheus"
-version = "0.15.1"
+version = "0.15.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bf0af7a0d7ced10c0151f870e5e3f3f8bc9ffc5992d32873566ca1f9169ae776"
+checksum = "b4f0c8427b39666bf970460908b213ec09b3b350f20c0c2eabcbba51704a08e6"
 dependencies = [
  "base64 0.22.1",
  "http-body-util",
- "hyper 1.3.1",
+ "hyper 1.5.0",
  "hyper-rustls",
  "hyper-util",
- "indexmap 2.2.6",
+ "indexmap 2.6.0",
  "ipnet",
- "metrics 0.23.0",
+ "metrics",
  "metrics-util",
  "quanta",
  "thiserror",
@@ -1977,17 +2223,6 @@ dependencies = [
  "tracing",
 ]
 
-[[package]]
-name = "metrics-macros"
-version = "0.7.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38b4faf00617defe497754acde3024865bc143d44a86799b24e191ecff91354f"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn 2.0.68",
-]
-
 [[package]]
 name = "metrics-util"
 version = "0.17.0"
@@ -1997,7 +2232,7 @@ dependencies = [
  "crossbeam-epoch",
  "crossbeam-utils",
  "hashbrown 0.14.5",
- "metrics 0.23.0",
+ "metrics",
  "num_cpus",
  "quanta",
  "sketches-ddsketch",
@@ -2011,9 +2246,9 @@ checksum = "6877bb514081ee2a7ff5ef9de3281f14a4dd4bceac4c09388074a6b5df8a139a"
 
 [[package]]
 name = "mime_guess"
-version = "2.0.4"
+version = "2.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4192263c238a5f0d0c6bfd21f336a313a4ce1c450542449ca191bb657b4642ef"
+checksum = "f7c44f8e672c00fe5308fa235f821cb4198414e1c77935c1ab6948d3fd78550e"
 dependencies = [
  "mime",
  "unicase",
@@ -2021,18 +2256,19 @@ dependencies = [
 
 [[package]]
 name = "minijinja"
-version = "2.0.2"
+version = "2.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e136ef580d7955019ab0a407b68d77c292a9976907e217900f3f76bc8f6dc1a4"
+checksum = "c9ca8daf4b0b4029777f1bc6e1aedd1aec7b74c276a43bc6f620a8e1a1c0a90e"
 dependencies = [
  "serde",
+ "serde_json",
 ]
 
 [[package]]
 name = "minijinja-contrib"
-version = "2.0.2"
+version = "2.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "15ee37078c98d31e510d6a7af488031a2c3ccacdb76c5c4fc98ddfe6d0e9da07"
+checksum = "39ffd46ee854be23604a20efd6c9655374fefbe4d44b949dc0f907305d92873a"
 dependencies = [
  "minijinja",
  "serde",
@@ -2051,19 +2287,29 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b8a240ddb74feaf34a79a7add65a741f3167852fba007066dcac1ca548d89c08"
 dependencies = [
  "adler",
+]
+
+[[package]]
+name = "miniz_oxide"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e2d80299ef12ff69b16a84bb182e3b9df68b5a91574d3d4fa6e41b65deec4df1"
+dependencies = [
+ "adler2",
  "simd-adler32",
 ]
 
 [[package]]
 name = "mio"
-version = "0.8.11"
+version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a4a650543ca06a924e8b371db273b2756685faae30f8487da1b56505a8f78b0c"
+checksum = "80e04d1dcff3aae0704555fe5fee3bcfaf3d1fdf8a7e521d5b9d2b42acb52cec"
 dependencies = [
+ "hermit-abi 0.3.9",
  "libc",
  "log",
  "wasi",
- "windows-sys 0.48.0",
+ "windows-sys 0.52.0",
 ]
 
 [[package]]
@@ -2090,7 +2336,7 @@ checksum = "a7ce64b975ed4f123575d11afd9491f2e37bbd5813fbfbc0f09ae1fbddea74e0"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -2156,7 +2402,7 @@ dependencies = [
  "bytes",
  "futures",
  "hostname",
- "hyper 0.14.29",
+ "hyper 0.14.31",
  "muxado",
  "once_cell",
  "parking_lot",
@@ -2180,7 +2426,19 @@ checksum = "ab2156c4fce2f8df6c499cc1c763e4394b7482525bf2a9701c9d79d215f519e4"
 dependencies = [
  "bitflags 2.6.0",
  "cfg-if",
- "cfg_aliases",
+ "cfg_aliases 0.1.1",
+ "libc",
+]
+
+[[package]]
+name = "nix"
+version = "0.29.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "71e2746dc3a24dd78b3cfcb7be93368c6de9963d30f43a6a73998a9cf4b17b46"
+dependencies = [
+ "bitflags 2.6.0",
+ "cfg-if",
+ "cfg_aliases 0.2.1",
  "libc",
 ]
 
@@ -2241,9 +2499,9 @@ dependencies = [
 
 [[package]]
 name = "num-bigint"
-version = "0.4.5"
+version = "0.4.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c165a9ab64cf766f73521c0dd2cfdff64f488b8f0b3e621face3462d3db536d7"
+checksum = "a5e44f723f1133c9deac646763579fdb3ac745e418f2a7af9cd0c431da1f20b9"
 dependencies = [
  "num-integer",
  "num-traits",
@@ -2278,7 +2536,7 @@ checksum = "ed3955f1a9c7c0c15e092f9c887db08b1fc683305fdf6eb6684f22555355e202"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -2328,7 +2586,7 @@ version = "1.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4161fcb6d602d4d2081af7c3a45852d875a03dd337a6bfdd6e06407b61342a43"
 dependencies = [
- "hermit-abi",
+ "hermit-abi 0.3.9",
  "libc",
 ]
 
@@ -2349,18 +2607,18 @@ checksum = "830b246a0e5f20af87141b25c173cd1b609bd7779a4617d6ec582abaf90870f3"
 
 [[package]]
 name = "object"
-version = "0.36.0"
+version = "0.36.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "576dfe1fc8f9df304abb159d767a29d0476f7750fbf8aa7ad07816004a207434"
+checksum = "aedf0a2d09c573ed1d8d85b30c119153926a2b36dce0ab28322c09a117a4683e"
 dependencies = [
  "memchr",
 ]
 
 [[package]]
 name = "once_cell"
-version = "1.19.0"
+version = "1.20.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92"
+checksum = "1261fe7e33c73b354eab43b1273a57c8f967d0391e80353e51f764ac02cf6775"
 
 [[package]]
 name = "onig"
@@ -2384,11 +2642,17 @@ dependencies = [
  "pkg-config",
 ]
 
+[[package]]
+name = "oorandom"
+version = "11.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b410bbe7e14ab526a0e86877eb47c6996a2bd7746f027ba551028c925390e4e9"
+
 [[package]]
 name = "openssl"
-version = "0.10.64"
+version = "0.10.68"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "95a0481286a310808298130d22dd1fef0fa571e05a8f44ec801801e84b216b1f"
+checksum = "6174bc48f102d208783c2c84bf931bb75927a617866870de8a4ea85597f871f5"
 dependencies = [
  "bitflags 2.6.0",
  "cfg-if",
@@ -2407,7 +2671,7 @@ checksum = "a948666b637a0f465e8564c73e89d4dde00d72d4d473cc972f390fc3dcee7d9c"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -2418,9 +2682,9 @@ checksum = "ff011a302c396a5197692431fc1948019154afc178baf7d8e37367442a4601cf"
 
 [[package]]
 name = "openssl-sys"
-version = "0.9.102"
+version = "0.9.104"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c597637d56fbc83893a35eb0dd04b2b8e7a50c91e64e9493e398b5df4fb45fa2"
+checksum = "45abf306cbf99debc8195b66b7346498d7b10c210de50418b5ccd7ceba08c741"
 dependencies = [
  "cc",
  "libc",
@@ -2446,7 +2710,7 @@ checksum = "1e32339a5dc40459130b3bd269e9892439f55b33e772d2a9d402a789baaf4e8a"
 dependencies = [
  "futures-core",
  "futures-sink",
- "indexmap 2.2.6",
+ "indexmap 2.6.0",
  "js-sys",
  "once_cell",
  "pin-project-lite",
@@ -2454,6 +2718,20 @@ dependencies = [
  "urlencoding",
 ]
 
+[[package]]
+name = "opentelemetry"
+version = "0.24.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4c365a63eec4f55b7efeceb724f1336f26a9cf3427b70e59e2cd2a5b947fba96"
+dependencies = [
+ "futures-core",
+ "futures-sink",
+ "js-sys",
+ "once_cell",
+ "pin-project-lite",
+ "thiserror",
+]
+
 [[package]]
 name = "opentelemetry-otlp"
 version = "0.13.0"
@@ -2547,7 +2825,25 @@ dependencies = [
  "glob",
  "once_cell",
  "opentelemetry 0.21.0",
- "ordered-float 4.2.0",
+ "ordered-float 4.4.0",
+ "percent-encoding",
+ "rand",
+ "thiserror",
+]
+
+[[package]]
+name = "opentelemetry_sdk"
+version = "0.24.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "692eac490ec80f24a17828d49b40b60f5aeaccdfe6a503f939713afd22bc28df"
+dependencies = [
+ "async-trait",
+ "futures-channel",
+ "futures-executor",
+ "futures-util",
+ "glob",
+ "once_cell",
+ "opentelemetry 0.24.0",
  "percent-encoding",
  "rand",
  "thiserror",
@@ -2570,9 +2866,9 @@ dependencies = [
 
 [[package]]
 name = "ordered-float"
-version = "4.2.0"
+version = "4.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a76df7075c7d4d01fdcb46c912dd17fba5b60c78ea480b475f2b6ab6f666584e"
+checksum = "83e7ccb95e240b7c9506a3d544f10d935e142cc90b0a1d56954fb44d89ad6b97"
 dependencies = [
  "num-traits",
 ]
@@ -2614,7 +2910,7 @@ dependencies = [
  "libc",
  "redox_syscall",
  "smallvec",
- "windows-targets 0.52.5",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -2636,34 +2932,34 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b4c5cc86750666a3ed20bdaf5ca2a0344f9c67674cae0515bec2da16fbaa47db"
 dependencies = [
  "fixedbitset",
- "indexmap 2.2.6",
+ "indexmap 2.6.0",
 ]
 
 [[package]]
 name = "pin-project"
-version = "1.1.5"
+version = "1.1.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b6bf43b791c5b9e34c3d182969b4abb522f9343702850a2e57f460d00d09b4b3"
+checksum = "be57f64e946e500c8ee36ef6331845d40a93055567ec57e8fae13efd33759b95"
 dependencies = [
  "pin-project-internal",
 ]
 
 [[package]]
 name = "pin-project-internal"
-version = "1.1.5"
+version = "1.1.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2f38a4412a78282e09a2cf38d195ea5420d15ba0602cb375210efbc877243965"
+checksum = "3c0f5fad0874fc7abcd4d750e76917eaebbecaa2c20bde22e1dbeeba8beb758c"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
 name = "pin-project-lite"
-version = "0.2.14"
+version = "0.2.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bda66fc9667c18cb2758a2ac84d1167245054bcf85d5d1aaa6923f45801bdd02"
+checksum = "915a1e146535de9163f3987b8944ed8cf49a18bb0056bcebcdcece385cece4ff"
 
 [[package]]
 name = "pin-utils"
@@ -2673,28 +2969,56 @@ checksum = "8b870d8c151b6f2fb93e84a13146138f05d02ed11c7e7c54f8826aaaf7c9f184"
 
 [[package]]
 name = "pkg-config"
-version = "0.3.30"
+version = "0.3.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d231b230927b5e4ad203db57bbcbee2802f6bce620b1e4a9024a07d94e2907ec"
+checksum = "953ec861398dccce10c670dfeaf3ec4911ca479e9c02154b3a215178c5f566f2"
+
+[[package]]
+name = "plotters"
+version = "0.3.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5aeb6f403d7a4911efb1e33402027fc44f29b5bf6def3effcc22d7bb75f2b747"
+dependencies = [
+ "num-traits",
+ "plotters-backend",
+ "plotters-svg",
+ "wasm-bindgen",
+ "web-sys",
+]
+
+[[package]]
+name = "plotters-backend"
+version = "0.3.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "df42e13c12958a16b3f7f4386b9ab1f3e7933914ecea48da7139435263a4172a"
+
+[[package]]
+name = "plotters-svg"
+version = "0.3.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "51bae2ac328883f7acdfea3d66a7c35751187f870bc81f94563733a154d7a670"
+dependencies = [
+ "plotters-backend",
+]
 
 [[package]]
 name = "png"
-version = "0.17.13"
+version = "0.17.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "06e4b0d3d1312775e782c86c91a111aa1f910cbb65e1337f9975b5f9a554b5e1"
+checksum = "52f9d46a34a05a6a57566bc2bfae066ef07585a6e3fa30fbbdff5936380623f0"
 dependencies = [
  "bitflags 1.3.2",
  "crc32fast",
  "fdeflate",
  "flate2",
- "miniz_oxide",
+ "miniz_oxide 0.8.0",
 ]
 
 [[package]]
 name = "portable-atomic"
-version = "1.6.0"
+version = "1.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7170ef9988bc169ba16dd36a7fa041e5c4cbeb6a35b76d4c03daded371eae7c0"
+checksum = "cc9c68a3f6da06753e9335d63e27f6b9754dd1920d941135b7ea8224f141adb2"
 
 [[package]]
 name = "powerfmt"
@@ -2704,18 +3028,21 @@ checksum = "439ee305def115ba05938db6eb1644ff94165c5ab5e9420d1c1bcedbba909391"
 
 [[package]]
 name = "ppv-lite86"
-version = "0.2.17"
+version = "0.2.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de"
+checksum = "77957b295656769bb8ad2b6a6b09d897d94f05c41b069aede1fcdaa675eaea04"
+dependencies = [
+ "zerocopy",
+]
 
 [[package]]
 name = "prettyplease"
-version = "0.2.20"
+version = "0.2.25"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5f12335488a2f3b0a83b14edad48dca9879ce89b2edd10e80237e4e852dd645e"
+checksum = "64d1ec885c64d0457d564db4ec299b2dae3f9c02808b8ad9c3a089c591b18033"
 dependencies = [
  "proc-macro2",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -2744,30 +3071,30 @@ dependencies = [
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.86"
+version = "1.0.89"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5e719e8df665df0d1c8fbfd238015744736151d4445ec0836b8e628aae103b77"
+checksum = "f139b0662de085916d1fb67d2b4169d1addddda1919e696f3252b740b629986e"
 dependencies = [
  "unicode-ident",
 ]
 
 [[package]]
 name = "profiling"
-version = "1.0.15"
+version = "1.0.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "43d84d1d7a6ac92673717f9f6d1518374ef257669c24ebc5ac25d5033828be58"
+checksum = "afbdc74edc00b6f6a218ca6a5364d6226a259d4b8ea1af4a0ea063f27e179f4d"
 dependencies = [
  "profiling-procmacros",
 ]
 
 [[package]]
 name = "profiling-procmacros"
-version = "1.0.15"
+version = "1.0.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8021cf59c8ec9c432cfc2526ac6b8aa508ecaf29cd415f271b8406c1b851c3fd"
+checksum = "a65f2e60fbf1063868558d69c6beacf412dc755f9fc020f514b7955fc914fe30"
 dependencies = [
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -2807,7 +3134,7 @@ dependencies = [
  "prost 0.12.6",
  "prost-types",
  "regex",
- "syn 2.0.68",
+ "syn 2.0.85",
  "tempfile",
 ]
 
@@ -2834,7 +3161,7 @@ dependencies = [
  "itertools 0.12.1",
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -2846,6 +3173,69 @@ dependencies = [
  "prost 0.12.6",
 ]
 
+[[package]]
+name = "pyo3"
+version = "0.22.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3d922163ba1f79c04bc49073ba7b32fd5a8d3b76a87c955921234b8e77333c51"
+dependencies = [
+ "cfg-if",
+ "indoc",
+ "libc",
+ "memoffset",
+ "once_cell",
+ "portable-atomic",
+ "pyo3-build-config",
+ "pyo3-ffi",
+ "pyo3-macros",
+ "unindent",
+]
+
+[[package]]
+name = "pyo3-build-config"
+version = "0.22.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bc38c5feeb496c8321091edf3d63e9a6829eab4b863b4a6a65f26f3e9cc6b179"
+dependencies = [
+ "once_cell",
+ "target-lexicon",
+]
+
+[[package]]
+name = "pyo3-ffi"
+version = "0.22.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "94845622d88ae274d2729fcefc850e63d7a3ddff5e3ce11bd88486db9f1d357d"
+dependencies = [
+ "libc",
+ "pyo3-build-config",
+]
+
+[[package]]
+name = "pyo3-macros"
+version = "0.22.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e655aad15e09b94ffdb3ce3d217acf652e26bbc37697ef012f5e5e348c716e5e"
+dependencies = [
+ "proc-macro2",
+ "pyo3-macros-backend",
+ "quote",
+ "syn 2.0.85",
+]
+
+[[package]]
+name = "pyo3-macros-backend"
+version = "0.22.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ae1e3f09eecd94618f60a455a23def79f79eba4dc561a97324bf9ac8c6df30ce"
+dependencies = [
+ "heck 0.5.0",
+ "proc-macro2",
+ "pyo3-build-config",
+ "quote",
+ "syn 2.0.85",
+]
+
 [[package]]
 name = "qoi"
 version = "0.4.1"
@@ -2878,9 +3268,9 @@ checksum = "a993555f31e5a609f617c12db6250dedcac1b0a85076912c436e6fc9b2c8e6a3"
 
 [[package]]
 name = "quote"
-version = "1.0.36"
+version = "1.0.37"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0fa76aaf39101c457836aec0ce2316dbdc3ab723cdda1c6bd4e6ad4208acaca7"
+checksum = "b5b9d34b8991d19d98081b46eacdd8eb58c6f2b201139f7c5f643cc155a633af"
 dependencies = [
  "proc-macro2",
 ]
@@ -2917,18 +3307,22 @@ dependencies = [
 
 [[package]]
 name = "ratatui"
-version = "0.23.0"
+version = "0.28.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2e2e4cd95294a85c3b4446e63ef054eea43e0205b1fd60120c16b74ff7ff96ad"
+checksum = "fdef7f9be5c0122f890d58bdf4d964349ba6a6161f705907526d891efabba57d"
 dependencies = [
  "bitflags 2.6.0",
  "cassowary",
+ "compact_str",
  "crossterm",
- "indoc",
- "itertools 0.11.0",
+ "instability",
+ "itertools 0.13.0",
+ "lru",
  "paste",
  "strum",
+ "strum_macros",
  "unicode-segmentation",
+ "unicode-truncate",
  "unicode-width",
 ]
 
@@ -2969,24 +3363,23 @@ dependencies = [
 
 [[package]]
 name = "ravif"
-version = "0.11.7"
+version = "0.11.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "67376f469e7e7840d0040bbf4b9b3334005bb167f814621326e4c7ab8cd6e944"
+checksum = "2413fd96bd0ea5cdeeb37eaf446a22e6ed7b981d792828721e74ded1980a45c6"
 dependencies = [
  "avif-serialize",
  "imgref",
  "loop9",
  "quick-error",
  "rav1e",
- "rayon",
  "rgb",
 ]
 
 [[package]]
 name = "raw-cpuid"
-version = "11.0.2"
+version = "11.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e29830cbb1290e404f24c73af91c5d8d631ce7e128691e9477556b540cd01ecd"
+checksum = "1ab240315c661615f2ee9f0f2cd32d5a7343a84d5ebcccb99d46e6637565e7b0"
 dependencies = [
  "bitflags 2.6.0",
 ]
@@ -3024,18 +3417,18 @@ dependencies = [
 
 [[package]]
 name = "redox_syscall"
-version = "0.5.2"
+version = "0.5.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c82cf8cff14456045f55ec4241383baeff27af886adb72ffb2162f99911de0fd"
+checksum = "9b6dfecf2c74bce2466cabf93f6664d6998a69eb21e39f4207930065b27b771f"
 dependencies = [
  "bitflags 2.6.0",
 ]
 
 [[package]]
 name = "redox_users"
-version = "0.4.5"
+version = "0.4.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bd283d9651eeda4b2a83a43c1c91b266c40fd76ecd39a50a8c630ae69dc72891"
+checksum = "ba009ff324d1fc1b900bd1fdb31564febe58a8ccc8a6fdbb93b543d33b13ca43"
 dependencies = [
  "getrandom",
  "libredox",
@@ -3044,14 +3437,14 @@ dependencies = [
 
 [[package]]
 name = "regex"
-version = "1.10.5"
+version = "1.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b91213439dad192326a0d7c6ee3955910425f441d7038e0d6933b0aec5c4517f"
+checksum = "b544ef1b4eac5dc2db33ea63606ae9ffcfac26c1416a2806ae0bf5f56b201191"
 dependencies = [
  "aho-corasick",
  "memchr",
- "regex-automata 0.4.7",
- "regex-syntax 0.8.4",
+ "regex-automata 0.4.8",
+ "regex-syntax 0.8.5",
 ]
 
 [[package]]
@@ -3065,13 +3458,13 @@ dependencies = [
 
 [[package]]
 name = "regex-automata"
-version = "0.4.7"
+version = "0.4.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38caf58cc5ef2fed281f89292ef23f6365465ed9a41b7a7754eb4e26496c92df"
+checksum = "368758f23274712b504848e9d5a6f010445cc8b87a7cdb4d7cbee666c1288da3"
 dependencies = [
  "aho-corasick",
  "memchr",
- "regex-syntax 0.8.4",
+ "regex-syntax 0.8.5",
 ]
 
 [[package]]
@@ -3082,9 +3475,9 @@ checksum = "f162c6dd7b008981e4d40210aca20b4bd0f9b60ca9271061b07f78537722f2e1"
 
 [[package]]
 name = "regex-syntax"
-version = "0.8.4"
+version = "0.8.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7a66a03ae7c801facd77a29370b4faec201768915ac14a721ba36f20bc9c209b"
+checksum = "2b15c43186be67a4fd63bee50d0303afffcef381492ebe2c5d87f324e1b8815c"
 
 [[package]]
 name = "reqwest"
@@ -3100,7 +3493,7 @@ dependencies = [
  "h2 0.3.26",
  "http 0.2.12",
  "http-body 0.4.6",
- "hyper 0.14.29",
+ "hyper 0.14.31",
  "hyper-tls",
  "ipnet",
  "js-sys",
@@ -3128,12 +3521,9 @@ dependencies = [
 
 [[package]]
 name = "rgb"
-version = "0.8.37"
+version = "0.8.50"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "05aaa8004b64fd573fc9d002f4e632d51ad4f026c2b5ba95fcb6c2f32c2c47d8"
-dependencies = [
- "bytemuck",
-]
+checksum = "57397d16646700483b67d2dd6511d79318f9d057fdbd21a4066aeac8b41d310a"
 
 [[package]]
 name = "ring"
@@ -3167,9 +3557,9 @@ dependencies = [
 
 [[package]]
 name = "rust-embed"
-version = "8.4.0"
+version = "8.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "19549741604902eb99a7ed0ee177a0663ee1eda51a29f71401f166e47e77806a"
+checksum = "fa66af4a4fdd5e7ebc276f115e895611a34739a9c1c01028383d612d550953c0"
 dependencies = [
  "rust-embed-impl",
  "rust-embed-utils",
@@ -3178,22 +3568,22 @@ dependencies = [
 
 [[package]]
 name = "rust-embed-impl"
-version = "8.4.0"
+version = "8.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cb9f96e283ec64401f30d3df8ee2aaeb2561f34c824381efa24a35f79bf40ee4"
+checksum = "6125dbc8867951125eec87294137f4e9c2c96566e61bf72c45095a7c77761478"
 dependencies = [
  "proc-macro2",
  "quote",
  "rust-embed-utils",
- "syn 2.0.68",
+ "syn 2.0.85",
  "walkdir",
 ]
 
 [[package]]
 name = "rust-embed-utils"
-version = "8.4.0"
+version = "8.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38c74a686185620830701348de757fd36bef4aa9680fd23c49fc539ddcc1af32"
+checksum = "2e5347777e9aacb56039b0e1f28785929a8a3b709e87482e7442c72e7c12529d"
 dependencies = [
  "sha2",
  "walkdir",
@@ -3213,18 +3603,18 @@ checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
 
 [[package]]
 name = "rustc_version"
-version = "0.4.0"
+version = "0.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bfa0f585226d2e68097d4f95d113b15b83a82e819ab25717ec0590d9584ef366"
+checksum = "cfcb3a22ef46e85b45de6ee7e79d063319ebb6594faafcf1c225ea92ab6e9b92"
 dependencies = [
  "semver",
 ]
 
 [[package]]
 name = "rustix"
-version = "0.38.34"
+version = "0.38.37"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "70dc5ec042f7a43c4a73241207cecc9873a06d45debb38b329f8541d85c2730f"
+checksum = "8acb788b847c24f28525660c4d7758620a7210875711f79e7f663cc152726811"
 dependencies = [
  "bitflags 2.6.0",
  "errno",
@@ -3261,9 +3651,9 @@ dependencies = [
 
 [[package]]
 name = "rustls"
-version = "0.23.10"
+version = "0.23.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "05cff451f60db80f490f3c182b77c35260baace73209e9cdbbe526bfe3a4d402"
+checksum = "5fbb44d7acc4e873d613422379f69f237a1b141928c02f6bc6ccfddddc2d7993"
 dependencies = [
  "aws-lc-rs",
  "log",
@@ -3276,12 +3666,12 @@ dependencies = [
 
 [[package]]
 name = "rustls-native-certs"
-version = "0.7.0"
+version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8f1fb85efa936c42c6d5fc28d2629bb51e4b2f4b8a5211e297d599cc5a093792"
+checksum = "fcaf18a4f2be7326cd874a5fa579fae794320a0f388d365dca7e480e55f83f8a"
 dependencies = [
  "openssl-probe",
- "rustls-pemfile 2.1.2",
+ "rustls-pemfile 2.2.0",
  "rustls-pki-types",
  "schannel",
  "security-framework",
@@ -3298,25 +3688,24 @@ dependencies = [
 
 [[package]]
 name = "rustls-pemfile"
-version = "2.1.2"
+version = "2.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "29993a25686778eb88d4189742cd713c9bce943bc54251a33509dc63cbacf73d"
+checksum = "dce314e5fee3f39953d46bb63bb8a46d40c2f8fb7cc5a3b6cab2bde9721d6e50"
 dependencies = [
- "base64 0.22.1",
  "rustls-pki-types",
 ]
 
 [[package]]
 name = "rustls-pki-types"
-version = "1.7.0"
+version = "1.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "976295e77ce332211c0d24d92c0e83e50f5c5f046d11082cea19f3df13a3562d"
+checksum = "16f1201b3c9a7ee8039bcadc17b7e605e2945b27eee7631788c1bd2b0643674b"
 
 [[package]]
 name = "rustls-webpki"
-version = "0.102.4"
+version = "0.102.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ff448f7e92e913c4b7d4c6d8e4540a1724b319b4152b8aef6d4cf8339712b33e"
+checksum = "64ca1bc8749bd4cf37b5ce386cc146580777b4e8572c7b97baf22c83f444bee9"
 dependencies = [
  "aws-lc-rs",
  "ring 0.17.8",
@@ -3326,9 +3715,9 @@ dependencies = [
 
 [[package]]
 name = "rustversion"
-version = "1.0.17"
+version = "1.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "955d28af4278de8121b7ebeb796b6a45735dc01436d898801014aced2773a3d6"
+checksum = "0e819f2bc632f285be6d7cd36e25940d45b2391dd6d9b939e79de557f7014248"
 
 [[package]]
 name = "ryu"
@@ -3347,11 +3736,11 @@ dependencies = [
 
 [[package]]
 name = "schannel"
-version = "0.1.23"
+version = "0.1.26"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fbc91545643bcf3a0bbb6569265615222618bdf33ce4ffbbd13c4bbd4c093534"
+checksum = "01227be5826fa0690321a2ba6c5cd57a19cf3f6a09e76973b58e61de6ab9d1c1"
 dependencies = [
- "windows-sys 0.52.0",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]
@@ -3360,6 +3749,12 @@ version = "1.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
 
+[[package]]
+name = "scratch"
+version = "1.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a3cf7c11c38cb994f3d40e8a8cde3bbd1f72a435e4c49e85d6553d8312306152"
+
 [[package]]
 name = "sct"
 version = "0.7.1"
@@ -3372,9 +3767,9 @@ dependencies = [
 
 [[package]]
 name = "security-framework"
-version = "2.11.0"
+version = "2.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c627723fd09706bacdb5cf41499e95098555af3c3c29d014dc3c458ef6be11c0"
+checksum = "897b2245f0b511c87893af39b033e5ca9cce68824c4d7e7630b5a1d339658d02"
 dependencies = [
  "bitflags 2.6.0",
  "core-foundation",
@@ -3385,9 +3780,9 @@ dependencies = [
 
 [[package]]
 name = "security-framework-sys"
-version = "2.11.0"
+version = "2.12.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "317936bbbd05227752583946b9e66d7ce3b489f84e11a94a510b4437fef407d7"
+checksum = "ea4a292869320c0272d7bc55a5a6aafaff59b4f63404a003887b679a2e05b4b6"
 dependencies = [
  "core-foundation-sys",
  "libc",
@@ -3404,31 +3799,42 @@ dependencies = [
 
 [[package]]
 name = "serde"
-version = "1.0.203"
+version = "1.0.213"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7253ab4de971e72fb7be983802300c30b5a7f0c2e56fab8abfc6a214307c0094"
+checksum = "3ea7893ff5e2466df8d720bb615088341b295f849602c6956047f8f80f0e9bc1"
 dependencies = [
  "serde_derive",
 ]
 
+[[package]]
+name = "serde_cbor"
+version = "0.11.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2bef2ebfde456fb76bbcf9f59315333decc4fda0b2b44b420243c11e0f5ec1f5"
+dependencies = [
+ "half 1.8.3",
+ "serde",
+]
+
 [[package]]
 name = "serde_derive"
-version = "1.0.203"
+version = "1.0.213"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "500cbc0ebeb6f46627f50f3f5811ccf6bf00643be300b4c3eabc0ef55dc5b5ba"
+checksum = "7e85ad2009c50b58e87caa8cd6dac16bdf511bbfb7af6c33df902396aa480fa5"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
 name = "serde_json"
-version = "1.0.118"
+version = "1.0.132"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d947f6b3163d8857ea16c4fa0dd4840d52f3041039a85decd46867eb1abef2e4"
+checksum = "d726bfaff4b320266d395898905d0eba0345aae23b54aee3a737e260fd46db03"
 dependencies = [
  "itoa",
+ "memchr",
  "ryu",
  "serde",
 ]
@@ -3445,9 +3851,9 @@ dependencies = [
 
 [[package]]
 name = "serde_spanned"
-version = "0.6.6"
+version = "0.6.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "79e674e01f999af37c49f70a6ede167a8a60b2503e56c5599532a65baa5969a0"
+checksum = "87607cb1398ed59d48732e575a4c28a7a8ebf2454b964fe3f224f2afc07909e1"
 dependencies = [
  "serde",
 ]
@@ -3502,9 +3908,9 @@ dependencies = [
 
 [[package]]
 name = "signal-hook-mio"
-version = "0.2.3"
+version = "0.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "29ad2e15f37ec9a6cc544097b78a1ec90001e9f71b81338ca39f430adaca99af"
+checksum = "34db1a06d485c9142248b7a054f034b349b212551f3dfd19c94d45a754a217cd"
 dependencies = [
  "libc",
  "mio",
@@ -3602,6 +4008,12 @@ dependencies = [
  "unicode-segmentation",
 ]
 
+[[package]]
+name = "static_assertions"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f"
+
 [[package]]
 name = "strsim"
 version = "0.11.1"
@@ -3610,24 +4022,24 @@ checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f"
 
 [[package]]
 name = "strum"
-version = "0.25.0"
+version = "0.26.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "290d54ea6f91c969195bdbcd7442c8c2a2ba87da8bf60a7ee86a235d4bc1e125"
+checksum = "8fec0f0aef304996cf250b31b5a10dee7980c85da9d759361292b8bca5a18f06"
 dependencies = [
  "strum_macros",
 ]
 
 [[package]]
 name = "strum_macros"
-version = "0.25.3"
+version = "0.26.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "23dc1fa9ac9c169a78ba62f0b841814b7abae11bdd047b9c58f893439e309ea0"
+checksum = "4c6bee85a5a24955dc440386795aa378cd9cf82acd5f764469152d2270e581be"
 dependencies = [
- "heck 0.4.1",
+ "heck 0.5.0",
  "proc-macro2",
  "quote",
  "rustversion",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -3649,9 +4061,9 @@ dependencies = [
 
 [[package]]
 name = "syn"
-version = "2.0.68"
+version = "2.0.85"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "901fa70d88b9d6c98022e23b4136f9f3e54e4662c3bc1bd1d84a42a9a0f0c1e9"
+checksum = "5023162dfcd14ef8f32034d8bcd4cc5ddc61ef7a247c024a33e24e1f24d21b56"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -3672,15 +4084,16 @@ checksum = "a7065abeca94b6a8a577f9bd45aa0867a2238b74e8eb67cf10d492bc39351394"
 
 [[package]]
 name = "sysinfo"
-version = "0.30.12"
+version = "0.30.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "732ffa00f53e6b2af46208fba5718d9662a421049204e156328b66791ffa15ae"
+checksum = "0a5b4ddaee55fb2bea2bf0e5000747e5f5c0de765e5a5ff87f4cd106439f4bb3"
 dependencies = [
  "cfg-if",
  "core-foundation-sys",
  "libc",
  "ntapi",
  "once_cell",
+ "rayon",
  "windows",
 ]
 
@@ -3744,29 +4157,62 @@ dependencies = [
 
 [[package]]
 name = "target-lexicon"
-version = "0.12.14"
+version = "0.12.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e1fc403891a21bcfb7c37834ba66a547a8f402146eba7265b5a6d88059c9ff2f"
+checksum = "61c41af27dd6d1e27b1b16b489db798443478cef1f06a660c96db617ba5de3b1"
 
 [[package]]
 name = "tempfile"
-version = "3.10.1"
+version = "3.13.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "85b77fafb263dd9d05cbeac119526425676db3784113aa9295c88498cbf8bff1"
+checksum = "f0f2c9fc62d0beef6951ccffd757e241266a2c833136efbe35af6cd2567dca5b"
 dependencies = [
  "cfg-if",
  "fastrand",
+ "once_cell",
  "rustix",
- "windows-sys 0.52.0",
+ "windows-sys 0.59.0",
+]
+
+[[package]]
+name = "termcolor"
+version = "1.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "06794f8f6c5c898b3275aebefa6b8a1cb24cd2c6c79397ab15774837a0bc5755"
+dependencies = [
+ "winapi-util",
+]
+
+[[package]]
+name = "text-generation-backends-trtllm"
+version = "2.4.0"
+dependencies = [
+ "async-stream",
+ "async-trait",
+ "clap 4.5.20",
+ "cmake",
+ "cxx",
+ "cxx-build",
+ "hashbrown 0.14.5",
+ "hf-hub",
+ "log",
+ "pkg-config",
+ "text-generation-router",
+ "thiserror",
+ "tokenizers",
+ "tokio",
+ "tokio-stream",
+ "tracing",
+ "tracing-opentelemetry 0.25.0",
+ "tracing-subscriber",
 ]
 
 [[package]]
 name = "text-generation-benchmark"
-version = "2.1.1"
+version = "2.4.0"
 dependencies = [
  "average",
- "clap",
- "crossterm",
+ "clap 4.5.20",
  "float-ord",
  "hf-hub",
  "ratatui",
@@ -3783,7 +4229,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-client"
-version = "2.1.1"
+version = "2.4.0"
 dependencies = [
  "async-trait",
  "base64 0.22.1",
@@ -3795,20 +4241,22 @@ dependencies = [
  "tokio",
  "tonic 0.10.2",
  "tonic-build",
- "tower",
+ "tower 0.4.13",
  "tracing",
 ]
 
 [[package]]
 name = "text-generation-launcher"
-version = "2.1.1"
+version = "2.4.0"
 dependencies = [
- "clap",
+ "clap 4.5.20",
  "ctrlc",
  "float_eq",
  "hf-hub",
- "nix",
+ "nix 0.28.0",
  "once_cell",
+ "pyo3",
+ "regex",
  "reqwest",
  "serde",
  "serde_json",
@@ -3820,13 +4268,15 @@ dependencies = [
 
 [[package]]
 name = "text-generation-router"
-version = "2.1.1"
+version = "2.4.0"
 dependencies = [
  "async-stream",
- "axum 0.7.5",
+ "async-trait",
+ "axum 0.7.7",
  "axum-tracing-opentelemetry",
  "base64 0.22.1",
- "clap",
+ "clap 4.5.20",
+ "csv",
  "futures",
  "futures-util",
  "hf-hub",
@@ -3834,7 +4284,7 @@ dependencies = [
  "init-tracing-opentelemetry",
  "itertools 0.10.5",
  "jsonschema",
- "metrics 0.21.1",
+ "metrics",
  "metrics-exporter-prometheus",
  "minijinja",
  "minijinja-contrib",
@@ -3843,12 +4293,13 @@ dependencies = [
  "once_cell",
  "opentelemetry 0.20.0",
  "opentelemetry-otlp",
+ "pyo3",
  "rand",
  "regex",
  "reqwest",
  "serde",
  "serde_json",
- "text-generation-client",
+ "sysinfo",
  "thiserror",
  "tokenizers",
  "tokio",
@@ -3857,29 +4308,140 @@ dependencies = [
  "tracing",
  "tracing-opentelemetry 0.21.0",
  "tracing-subscriber",
+ "ureq",
  "utoipa",
  "utoipa-swagger-ui",
+ "uuid",
  "vergen",
 ]
 
+[[package]]
+name = "text-generation-router-v2"
+version = "2.4.0"
+dependencies = [
+ "async-stream",
+ "async-trait",
+ "axum 0.7.7",
+ "axum-tracing-opentelemetry",
+ "base64 0.22.1",
+ "clap 4.5.20",
+ "futures",
+ "futures-util",
+ "grpc-metadata",
+ "hf-hub",
+ "image",
+ "init-tracing-opentelemetry",
+ "jsonschema",
+ "metrics",
+ "metrics-exporter-prometheus",
+ "minijinja",
+ "minijinja-contrib",
+ "nohash-hasher",
+ "once_cell",
+ "opentelemetry 0.20.0",
+ "opentelemetry-otlp",
+ "prost 0.12.6",
+ "prost-build",
+ "rand",
+ "regex",
+ "reqwest",
+ "serde",
+ "serde_json",
+ "slotmap",
+ "text-generation-router",
+ "thiserror",
+ "tokenizers",
+ "tokio",
+ "tokio-stream",
+ "tonic 0.10.2",
+ "tonic-build",
+ "tower 0.4.13",
+ "tower-http",
+ "tracing",
+ "tracing-opentelemetry 0.21.0",
+ "tracing-subscriber",
+ "utoipa",
+ "utoipa-swagger-ui",
+]
+
+[[package]]
+name = "text-generation-router-v3"
+version = "2.4.0"
+dependencies = [
+ "async-stream",
+ "async-trait",
+ "axum 0.7.7",
+ "axum-tracing-opentelemetry",
+ "base64 0.22.1",
+ "clap 4.5.20",
+ "criterion",
+ "futures",
+ "futures-util",
+ "grpc-metadata",
+ "hf-hub",
+ "image",
+ "init-tracing-opentelemetry",
+ "itertools 0.13.0",
+ "jsonschema",
+ "metrics",
+ "metrics-exporter-prometheus",
+ "minijinja",
+ "minijinja-contrib",
+ "nohash-hasher",
+ "once_cell",
+ "opentelemetry 0.20.0",
+ "opentelemetry-otlp",
+ "prost 0.12.6",
+ "prost-build",
+ "rand",
+ "regex",
+ "reqwest",
+ "serde",
+ "serde_json",
+ "slotmap",
+ "text-generation-router",
+ "thiserror",
+ "tokenizers",
+ "tokio",
+ "tokio-stream",
+ "tonic 0.10.2",
+ "tonic-build",
+ "tower 0.4.13",
+ "tower-http",
+ "tracing",
+ "tracing-opentelemetry 0.21.0",
+ "tracing-subscriber",
+ "utoipa",
+ "utoipa-swagger-ui",
+]
+
+[[package]]
+name = "textwrap"
+version = "0.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d326610f408c7a4eb6f51c37c330e496b08506c9457c9d34287ecc38809fb060"
+dependencies = [
+ "unicode-width",
+]
+
 [[package]]
 name = "thiserror"
-version = "1.0.61"
+version = "1.0.65"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c546c80d6be4bc6a00c0f01730c08df82eaa7a7a61f11d656526506112cc1709"
+checksum = "5d11abd9594d9b38965ef50805c5e469ca9cc6f197f883f717e0269a3057b3d5"
 dependencies = [
  "thiserror-impl",
 ]
 
 [[package]]
 name = "thiserror-impl"
-version = "1.0.61"
+version = "1.0.65"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "46c3384250002a6d5af4d114f2845d37b57521033f30d5c3f46c4d70e1197533"
+checksum = "ae71770322cbd277e69d762a16c444af02aa0575ac0d174f0b9562d3b37f8602"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -3936,11 +4498,21 @@ dependencies = [
  "time-core",
 ]
 
+[[package]]
+name = "tinytemplate"
+version = "1.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "be4d6b5f19ff7664e8c98d03e2139cb510db9b0a60b55f8e8709b689d939b6bc"
+dependencies = [
+ "serde",
+ "serde_json",
+]
+
 [[package]]
 name = "tinyvec"
-version = "1.6.1"
+version = "1.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c55115c6fbe2d2bef26eb09ad74bde02d8255476fc0c7b515ef09fbb35742d82"
+checksum = "445e881f4f6d382d5f27c034e25eb92edd7c784ceab92a0937db7f2e9471b938"
 dependencies = [
  "tinyvec_macros",
 ]
@@ -3953,9 +4525,9 @@ checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
 
 [[package]]
 name = "tokenizers"
-version = "0.19.1"
+version = "0.20.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e500fad1dd3af3d626327e6a3fe5050e664a6eaa4708b8ca92f1794aaf73e6fd"
+checksum = "b172ffa9a2e5c31bbddc940cd5725d933ced983a9333bbebc4c7eda3bbce1557"
 dependencies = [
  "aho-corasick",
  "derive_builder",
@@ -3974,7 +4546,7 @@ dependencies = [
  "rayon",
  "rayon-cond",
  "regex",
- "regex-syntax 0.8.4",
+ "regex-syntax 0.8.5",
  "serde",
  "serde_json",
  "spm_precompiled",
@@ -3986,21 +4558,20 @@ dependencies = [
 
 [[package]]
 name = "tokio"
-version = "1.38.0"
+version = "1.41.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ba4f4a02a7a80d6f274636f0aa95c7e383b912d41fe721a31f29e29698585a4a"
+checksum = "145f3413504347a2be84393cc8a7d2fb4d863b375909ea59f2158261aa258bbb"
 dependencies = [
  "backtrace",
  "bytes",
  "libc",
  "mio",
- "num_cpus",
  "parking_lot",
  "pin-project-lite",
  "signal-hook-registry",
  "socket2",
  "tokio-macros",
- "windows-sys 0.48.0",
+ "windows-sys 0.52.0",
 ]
 
 [[package]]
@@ -4015,13 +4586,13 @@ dependencies = [
 
 [[package]]
 name = "tokio-macros"
-version = "2.3.0"
+version = "2.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5f5ae998a069d4b5aba8ee9dad856af7d520c3699e6159b185c2acd48155d39a"
+checksum = "693d596312e88961bc67d7f1f97af8a70227d9f90c31bba5806eec004978d752"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -4051,16 +4622,16 @@ version = "0.26.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0c7bc40d0e5a97695bb96e27995cd3a08538541b0a846f65bba7a359f36700d4"
 dependencies = [
- "rustls 0.23.10",
+ "rustls 0.23.15",
  "rustls-pki-types",
  "tokio",
 ]
 
 [[package]]
 name = "tokio-stream"
-version = "0.1.15"
+version = "0.1.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "267ac89e0bec6e691e5813911606935d77c476ff49024f98abcea3e7b15e37af"
+checksum = "4f4e6ce100d0eb49a2734f8c0812bcd324cf357d21810932c5df6b96ef2b86f1"
 dependencies = [
  "futures-core",
  "pin-project-lite",
@@ -4069,9 +4640,9 @@ dependencies = [
 
 [[package]]
 name = "tokio-util"
-version = "0.7.11"
+version = "0.7.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9cf6b47b3771c49ac75ad09a6162f53ad4b8088b76ac60e8ec1455b31a189fe1"
+checksum = "61e7c3654c13bcd040d4a03abee2c75b1d14a37b423cf5a813ceae1cc903ec6a"
 dependencies = [
  "bytes",
  "futures-core",
@@ -4083,9 +4654,9 @@ dependencies = [
 
 [[package]]
 name = "toml"
-version = "0.8.14"
+version = "0.8.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6f49eb2ab21d2f26bd6db7bf383edc527a7ebaee412d17af4d40fdccd442f335"
+checksum = "a1ed1f98e3fdc28d6d910e6737ae6ab1a93bf1985935a1193e68f93eeb68d24e"
 dependencies = [
  "serde",
  "serde_spanned",
@@ -4095,20 +4666,20 @@ dependencies = [
 
 [[package]]
 name = "toml_datetime"
-version = "0.6.6"
+version = "0.6.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4badfd56924ae69bcc9039335b2e017639ce3f9b001c393c1b2d1ef846ce2cbf"
+checksum = "0dd7358ecb8fc2f8d014bf86f6f638ce72ba252a2c3a2572f2a795f1d23efb41"
 dependencies = [
  "serde",
 ]
 
 [[package]]
 name = "toml_edit"
-version = "0.22.14"
+version = "0.22.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f21c7aaf97f1bd9ca9d4f9e73b0a6c74bd5afef56f2bc931943a6e1c37e04e38"
+checksum = "4ae48d6208a266e853d946088ed816055e556cc6028c5e8e2b84d9fa5dd7c7f5"
 dependencies = [
- "indexmap 2.2.6",
+ "indexmap 2.6.0",
  "serde",
  "serde_spanned",
  "toml_datetime",
@@ -4130,14 +4701,14 @@ dependencies = [
  "h2 0.3.26",
  "http 0.2.12",
  "http-body 0.4.6",
- "hyper 0.14.29",
+ "hyper 0.14.31",
  "hyper-timeout",
  "percent-encoding",
  "pin-project",
  "prost 0.11.9",
  "tokio",
  "tokio-stream",
- "tower",
+ "tower 0.4.13",
  "tower-layer",
  "tower-service",
  "tracing",
@@ -4157,14 +4728,14 @@ dependencies = [
  "h2 0.3.26",
  "http 0.2.12",
  "http-body 0.4.6",
- "hyper 0.14.29",
+ "hyper 0.14.31",
  "hyper-timeout",
  "percent-encoding",
  "pin-project",
  "prost 0.12.6",
  "tokio",
  "tokio-stream",
- "tower",
+ "tower 0.4.13",
  "tower-layer",
  "tower-service",
  "tracing",
@@ -4180,7 +4751,7 @@ dependencies = [
  "proc-macro2",
  "prost-build",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -4203,6 +4774,22 @@ dependencies = [
  "tracing",
 ]
 
+[[package]]
+name = "tower"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2873938d487c3cfb9aed7546dc9f2711d867c9f90c46b889989a2cb84eba6b4f"
+dependencies = [
+ "futures-core",
+ "futures-util",
+ "pin-project-lite",
+ "sync_wrapper 0.1.2",
+ "tokio",
+ "tower-layer",
+ "tower-service",
+ "tracing",
+]
+
 [[package]]
 name = "tower-http"
 version = "0.5.2"
@@ -4212,7 +4799,7 @@ dependencies = [
  "bitflags 2.6.0",
  "bytes",
  "http 1.1.0",
- "http-body 1.0.0",
+ "http-body 1.0.1",
  "http-body-util",
  "pin-project-lite",
  "tower-layer",
@@ -4221,15 +4808,15 @@ dependencies = [
 
 [[package]]
 name = "tower-layer"
-version = "0.3.2"
+version = "0.3.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c20c8dbed6283a09604c3e69b4b7eeb54e298b8a600d4d5ecb5ad39de609f1d0"
+checksum = "121c2a6cda46980bb0fcd1647ffaf6cd3fc79a013de288782836f6df9c48780e"
 
 [[package]]
 name = "tower-service"
-version = "0.3.2"
+version = "0.3.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b6bc1c9ce2b5135ac7f93c72918fc37feb872bdc6a5533a8b85eb4b86bfdae52"
+checksum = "8df9b6e13f2d32c91b9bd719c00d1958837bc7dec474d94952798cc8e69eeec3"
 
 [[package]]
 name = "tracing"
@@ -4251,7 +4838,7 @@ checksum = "34704c8d6ebcbc939824180af020566b01a7c01f80641264eba0999f6c2b6be7"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -4317,7 +4904,25 @@ dependencies = [
  "tracing-core",
  "tracing-log 0.2.0",
  "tracing-subscriber",
- "web-time",
+ "web-time 0.2.4",
+]
+
+[[package]]
+name = "tracing-opentelemetry"
+version = "0.25.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a9784ed4da7d921bc8df6963f8c80a0e4ce34ba6ba76668acadd3edbd985ff3b"
+dependencies = [
+ "js-sys",
+ "once_cell",
+ "opentelemetry 0.24.0",
+ "opentelemetry_sdk 0.24.1",
+ "smallvec",
+ "tracing",
+ "tracing-core",
+ "tracing-log 0.2.0",
+ "tracing-subscriber",
+ "web-time 1.1.0",
 ]
 
 [[package]]
@@ -4377,30 +4982,27 @@ checksum = "42ff0bf0c66b8238c6f3b578df37d0b7848e55df8577b3f74f92a69acceeb825"
 
 [[package]]
 name = "unicase"
-version = "2.7.0"
+version = "2.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f7d2d4dafb69621809a81864c9c1b864479e1235c0dd4e199924b9742439ed89"
-dependencies = [
- "version_check",
-]
+checksum = "7e51b68083f157f853b6379db119d1c1be0e6e4dec98101079dec41f6f5cf6df"
 
 [[package]]
 name = "unicode-bidi"
-version = "0.3.15"
+version = "0.3.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "08f95100a766bf4f8f28f90d77e0a5461bbdb219042e7679bebe79004fed8d75"
+checksum = "5ab17db44d7388991a428b2ee655ce0c212e862eff1768a455c58f9aad6e7893"
 
 [[package]]
 name = "unicode-ident"
-version = "1.0.12"
+version = "1.0.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
+checksum = "e91b56cd4cadaeb79bbf1a5645f6b4f8dc5bde8834ad5894a8db35fda9efa1fe"
 
 [[package]]
 name = "unicode-normalization"
-version = "0.1.23"
+version = "0.1.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a56d1686db2308d901306f92a263857ef59ea39678a5458e7cb17f01415101f5"
+checksum = "5033c97c4262335cded6d6fc3e5c18ab755e1a3dc96376350f3d8e9f009ad956"
 dependencies = [
  "tinyvec",
 ]
@@ -4416,15 +5018,26 @@ dependencies = [
 
 [[package]]
 name = "unicode-segmentation"
-version = "1.11.0"
+version = "1.12.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f6ccf251212114b54433ec949fd6a7841275f9ada20dddd2f29e9ceea4501493"
+
+[[package]]
+name = "unicode-truncate"
+version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d4c87d22b6e3f4a18d4d40ef354e97c90fcb14dd91d7dc0aa9d8a1172ebf7202"
+checksum = "b3644627a5af5fa321c95b9b235a72fd24cd29c648c2c379431e6628655627bf"
+dependencies = [
+ "itertools 0.13.0",
+ "unicode-segmentation",
+ "unicode-width",
+]
 
 [[package]]
 name = "unicode-width"
-version = "0.1.13"
+version = "0.1.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0336d538f7abc86d282a4189614dfaa90810dfc2c6f6427eaf88e16311dd225d"
+checksum = "7dd6e30e90baa6f72411720665d41d89b9a3d039dc45b8faea1ddd07f617f6af"
 
 [[package]]
 name = "unicode_categories"
@@ -4432,6 +5045,12 @@ version = "0.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "39ec24b3121d976906ece63c9daad25b85969647682eee313cb5779fdd69e14e"
 
+[[package]]
+name = "unindent"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c7de7d73e1754487cb58364ee906a499937a0dfabd86bcb980fa99ec8c8fa2ce"
+
 [[package]]
 name = "untrusted"
 version = "0.7.1"
@@ -4493,7 +5112,7 @@ version = "4.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c5afb1a60e207dca502682537fefcfd9921e71d0b83e9576060f09abc6efab23"
 dependencies = [
- "indexmap 2.2.6",
+ "indexmap 2.6.0",
  "serde",
  "serde_json",
  "utoipa-gen",
@@ -4501,15 +5120,15 @@ dependencies = [
 
 [[package]]
 name = "utoipa-gen"
-version = "4.3.0"
+version = "4.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7bf0e16c02bc4bf5322ab65f10ab1149bdbcaa782cba66dc7057370a3f8190be"
+checksum = "20c24e8ab68ff9ee746aad22d39b5535601e6416d1b0feeabf78be986a5c4392"
 dependencies = [
  "proc-macro-error",
  "proc-macro2",
  "quote",
  "regex",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -4518,7 +5137,7 @@ version = "6.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0b39868d43c011961e04b41623e050aedf2cc93652562ff7935ce0f819aaf2da"
 dependencies = [
- "axum 0.7.5",
+ "axum 0.7.7",
  "mime_guess",
  "regex",
  "rust-embed",
@@ -4530,9 +5149,25 @@ dependencies = [
 
 [[package]]
 name = "uuid"
-version = "1.9.1"
+version = "1.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5de17fd2f7da591098415cff336e12965a28061ddace43b59cb3c430179c9439"
+checksum = "f8c5f0a0af699448548ad1a2fbf920fb4bee257eae39953ba95cb84891a0446a"
+dependencies = [
+ "getrandom",
+ "rand",
+ "uuid-macro-internal",
+]
+
+[[package]]
+name = "uuid-macro-internal"
+version = "1.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6b91f57fe13a38d0ce9e28a03463d8d3c2468ed03d75375110ec71d93b449a08"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.85",
+]
 
 [[package]]
 name = "v_frame"
@@ -4559,9 +5194,9 @@ checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"
 
 [[package]]
 name = "vergen"
-version = "8.3.1"
+version = "8.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e27d6bdd219887a9eadd19e1c34f32e47fa332301184935c6d9bca26f3cca525"
+checksum = "2990d9ea5967266ea0ccf413a4aa5c42a93dbcfda9cb49a97de6931726b12566"
 dependencies = [
  "anyhow",
  "cargo_metadata",
@@ -4581,9 +5216,9 @@ checksum = "852e951cb7832cb45cb1169900d19760cfa39b82bc0ea9c0e5a14ae88411c98b"
 
 [[package]]
 name = "version_check"
-version = "0.9.4"
+version = "0.9.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "49874b5167b65d7193b8aba1567f5c7d93d001cafc34600cee003eda787e483f"
+checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
 
 [[package]]
 name = "walkdir"
@@ -4612,34 +5247,35 @@ checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
 
 [[package]]
 name = "wasm-bindgen"
-version = "0.2.92"
+version = "0.2.95"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4be2531df63900aeb2bca0daaaddec08491ee64ceecbee5076636a3b026795a8"
+checksum = "128d1e363af62632b8eb57219c8fd7877144af57558fb2ef0368d0087bddeb2e"
 dependencies = [
  "cfg-if",
+ "once_cell",
  "wasm-bindgen-macro",
 ]
 
 [[package]]
 name = "wasm-bindgen-backend"
-version = "0.2.92"
+version = "0.2.95"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "614d787b966d3989fa7bb98a654e369c762374fd3213d212cfc0251257e747da"
+checksum = "cb6dd4d3ca0ddffd1dd1c9c04f94b868c37ff5fac97c30b97cff2d74fce3a358"
 dependencies = [
  "bumpalo",
  "log",
  "once_cell",
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
  "wasm-bindgen-shared",
 ]
 
 [[package]]
 name = "wasm-bindgen-futures"
-version = "0.4.42"
+version = "0.4.45"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "76bc14366121efc8dbb487ab05bcc9d346b3b5ec0eaa76e46594cabbe51762c0"
+checksum = "cc7ec4f8827a71586374db3e87abdb5a2bb3a15afed140221307c3ec06b1f63b"
 dependencies = [
  "cfg-if",
  "js-sys",
@@ -4649,9 +5285,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro"
-version = "0.2.92"
+version = "0.2.95"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a1f8823de937b71b9460c0c34e25f3da88250760bec0ebac694b49997550d726"
+checksum = "e79384be7f8f5a9dd5d7167216f022090cf1f9ec128e6e6a482a2cb5c5422c56"
 dependencies = [
  "quote",
  "wasm-bindgen-macro-support",
@@ -4659,28 +5295,28 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro-support"
-version = "0.2.92"
+version = "0.2.95"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e94f17b526d0a461a191c78ea52bbce64071ed5c04c9ffe424dcb38f74171bb7"
+checksum = "26c6ab57572f7a24a4985830b120de1594465e5d500f24afe89e16b4e833ef68"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
  "wasm-bindgen-backend",
  "wasm-bindgen-shared",
 ]
 
 [[package]]
 name = "wasm-bindgen-shared"
-version = "0.2.92"
+version = "0.2.95"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "af190c94f2773fdb3729c55b007a722abb5384da03bc0986df4c289bf5567e96"
+checksum = "65fc09f10666a9f147042251e0dda9c18f166ff7de300607007e96bdebc1068d"
 
 [[package]]
 name = "web-sys"
-version = "0.3.69"
+version = "0.3.72"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "77afa9a11836342370f4817622a2f0f418b134426d91a82dfb48f532d2ec13ef"
+checksum = "f6488b90108c040df0fe62fa815cbdee25124641df01814dd7282749234c6112"
 dependencies = [
  "js-sys",
  "wasm-bindgen",
@@ -4696,6 +5332,16 @@ dependencies = [
  "wasm-bindgen",
 ]
 
+[[package]]
+name = "web-time"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5a6580f308b1fad9207618087a65c04e7a10bc77e02c8e84e9b00dd4b12fa0bb"
+dependencies = [
+ "js-sys",
+ "wasm-bindgen",
+]
+
 [[package]]
 name = "webpki"
 version = "0.22.4"
@@ -4708,9 +5354,9 @@ dependencies = [
 
 [[package]]
 name = "webpki-roots"
-version = "0.26.3"
+version = "0.26.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bd7c23921eeb1713a4e851530e9b9756e4fb0e89978582942612524cf09f01cd"
+checksum = "841c67bff177718f1d4dfefde8d8f0e78f9b6589319ba88312f567fc5841a958"
 dependencies = [
  "rustls-pki-types",
 ]
@@ -4751,11 +5397,11 @@ checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
 
 [[package]]
 name = "winapi-util"
-version = "0.1.8"
+version = "0.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4d4cc384e1e73b93bafa6fb4f1df8c41695c8a91cf9c4c64358067d15a7b6c6b"
+checksum = "cf221c93e13a30d793f7645a0e7762c55d169dbb0a49671918a2319d289b10bb"
 dependencies = [
- "windows-sys 0.52.0",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]
@@ -4771,7 +5417,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e48a53791691ab099e5e2ad123536d0fff50652600abaf43bbf952894110d0be"
 dependencies = [
  "windows-core",
- "windows-targets 0.52.5",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -4780,7 +5426,7 @@ version = "0.52.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "33ab640c8d7e35bf8ba19b884ba838ceb4fba93a4e8c65a9059d08afcfc683d9"
 dependencies = [
- "windows-targets 0.52.5",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -4807,7 +5453,16 @@ version = "0.52.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
 dependencies = [
- "windows-targets 0.52.5",
+ "windows-targets 0.52.6",
+]
+
+[[package]]
+name = "windows-sys"
+version = "0.59.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b"
+dependencies = [
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -4842,18 +5497,18 @@ dependencies = [
 
 [[package]]
 name = "windows-targets"
-version = "0.52.5"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6f0713a46559409d202e70e28227288446bf7841d3211583a4b53e3f6d96e7eb"
+checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
 dependencies = [
- "windows_aarch64_gnullvm 0.52.5",
- "windows_aarch64_msvc 0.52.5",
- "windows_i686_gnu 0.52.5",
+ "windows_aarch64_gnullvm 0.52.6",
+ "windows_aarch64_msvc 0.52.6",
+ "windows_i686_gnu 0.52.6",
  "windows_i686_gnullvm",
- "windows_i686_msvc 0.52.5",
- "windows_x86_64_gnu 0.52.5",
- "windows_x86_64_gnullvm 0.52.5",
- "windows_x86_64_msvc 0.52.5",
+ "windows_i686_msvc 0.52.6",
+ "windows_x86_64_gnu 0.52.6",
+ "windows_x86_64_gnullvm 0.52.6",
+ "windows_x86_64_msvc 0.52.6",
 ]
 
 [[package]]
@@ -4870,9 +5525,9 @@ checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
 
 [[package]]
 name = "windows_aarch64_gnullvm"
-version = "0.52.5"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7088eed71e8b8dda258ecc8bac5fb1153c5cffaf2578fc8ff5d61e23578d3263"
+checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
 
 [[package]]
 name = "windows_aarch64_msvc"
@@ -4888,9 +5543,9 @@ checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
 
 [[package]]
 name = "windows_aarch64_msvc"
-version = "0.52.5"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9985fd1504e250c615ca5f281c3f7a6da76213ebd5ccc9561496568a2752afb6"
+checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
 
 [[package]]
 name = "windows_i686_gnu"
@@ -4906,15 +5561,15 @@ checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
 
 [[package]]
 name = "windows_i686_gnu"
-version = "0.52.5"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "88ba073cf16d5372720ec942a8ccbf61626074c6d4dd2e745299726ce8b89670"
+checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
 
 [[package]]
 name = "windows_i686_gnullvm"
-version = "0.52.5"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "87f4261229030a858f36b459e748ae97545d6f1ec60e5e0d6a3d32e0dc232ee9"
+checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
 
 [[package]]
 name = "windows_i686_msvc"
@@ -4930,9 +5585,9 @@ checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
 
 [[package]]
 name = "windows_i686_msvc"
-version = "0.52.5"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "db3c2bf3d13d5b658be73463284eaf12830ac9a26a90c717b7f771dfe97487bf"
+checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
 
 [[package]]
 name = "windows_x86_64_gnu"
@@ -4948,9 +5603,9 @@ checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
 
 [[package]]
 name = "windows_x86_64_gnu"
-version = "0.52.5"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4e4246f76bdeff09eb48875a0fd3e2af6aada79d409d33011886d3e1581517d9"
+checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
 
 [[package]]
 name = "windows_x86_64_gnullvm"
@@ -4966,9 +5621,9 @@ checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
 
 [[package]]
 name = "windows_x86_64_gnullvm"
-version = "0.52.5"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "852298e482cd67c356ddd9570386e2862b5673c85bd5f88df9ab6802b334c596"
+checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
 
 [[package]]
 name = "windows_x86_64_msvc"
@@ -4984,15 +5639,15 @@ checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
 
 [[package]]
 name = "windows_x86_64_msvc"
-version = "0.52.5"
+version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bec47e5bfd1bff0eeaf6d8b485cc1074891a197ab4225d504cb7a1ab88b02bf0"
+checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
 
 [[package]]
 name = "winnow"
-version = "0.6.13"
+version = "0.6.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "59b5e5f6c299a3c7890b876a2a587f3115162487e704907d9b6cd29473052ba1"
+checksum = "36c1fec1a2bb5866f07c25f68c26e565c4c200aebb96d7e55710c19d3e8ac49b"
 dependencies = [
  "memchr",
 ]
@@ -5009,22 +5664,23 @@ dependencies = [
 
 [[package]]
 name = "zerocopy"
-version = "0.7.34"
+version = "0.7.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ae87e3fcd617500e5d106f0380cf7b77f3c6092aae37191433159dda23cfb087"
+checksum = "1b9b4fd18abc82b8136838da5d50bae7bdea537c574d8dc1a34ed098d6c166f0"
 dependencies = [
+ "byteorder",
  "zerocopy-derive",
 ]
 
 [[package]]
 name = "zerocopy-derive"
-version = "0.7.34"
+version = "0.7.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "15e934569e47891f7d9411f1a451d947a60e000ab3bd24fbb970f000387d1b3b"
+checksum = "fa4f8080344d4671fb4e831a13ad1e68092748387dfc4f55e356242fae12ce3e"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.68",
+ "syn 2.0.85",
 ]
 
 [[package]]
@@ -5032,20 +5688,6 @@ name = "zeroize"
 version = "1.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ced3678a2879b30306d323f4542626697a464a97c0a07c9aebf7ebca65cd4dde"
-dependencies = [
- "zeroize_derive",
-]
-
-[[package]]
-name = "zeroize_derive"
-version = "1.4.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ce36e65b0d2999d2aafac989fb249189a141aee1f53c612c1f37d72631959f69"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn 2.0.68",
-]
 
 [[package]]
 name = "zip"
@@ -5076,9 +5718,9 @@ dependencies = [
 
 [[package]]
 name = "zune-jpeg"
-version = "0.4.11"
+version = "0.4.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec866b44a2a1fd6133d363f073ca1b179f438f99e7e5bfb1e33f7181facfe448"
+checksum = "16099418600b4d8f028622f73ff6e3deaabdff330fb9a2a131dea781ee8b0768"
 dependencies = [
  "zune-core",
 ]

Cargo.toml

 [workspace]
 members = [
-    "benchmark",
-    "router",
-    "router/client",
-    "router/grpc-metadata",
-    "launcher"
+  "benchmark",
+  "backends/v2",
+  "backends/v3",
+  "backends/grpc-metadata",
+  "backends/trtllm",
+  "launcher",
+  "router"
+]
+default-members = [
+  "benchmark",
+  "backends/v2",
+  "backends/v3",
+  "backends/grpc-metadata",
+  # "backends/trtllm",
+  "launcher",
+  "router"
 ]
 resolver = "2"
 
 [workspace.package]
-version = "2.1.1"
+version = "2.4.0"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"
 
 [workspace.dependencies]
 base64 = "0.22.0"
-tokenizers = { version = "0.19.1", features = ["http"] }
+tokenizers = { version = "0.20.0", features = ["http"] }
 hf-hub = { version = "0.3.1", features = ["tokio"] }
+metrics = { version = "0.23.0" }
+metrics-exporter-prometheus = { version = "0.15.1", features = [] }
+minijinja = { version = "2.2.0", features = ["json"] }
+minijinja-contrib = { version = "2.0.2", features = ["pycompat"] }
+pyo3 = { version = "0.22.2", features = ["auto-initialize"] }
 
 [profile.release]
 incremental = true

Dockerfile

 # Rust builder
-FROM lukemathwalker/cargo-chef:latest-rust-1.79 AS chef
+FROM lukemathwalker/cargo-chef:latest-rust-1.80.1 AS chef
 WORKDIR /usr/src
 
 ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
@@ -11,11 +11,15 @@ COPY rust-toolchain.toml rust-toolchain.toml
 COPY proto proto
 COPY benchmark benchmark
 COPY router router
+COPY backends backends
 COPY launcher launcher
+
 RUN cargo chef prepare --recipe-path recipe.json
 
 FROM chef AS builder
 
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
+    python3.11-dev
 RUN PROTOC_ZIP=protoc-21.12-linux-x86_64.zip && \
     curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v21.12/$PROTOC_ZIP && \
     unzip -o $PROTOC_ZIP -d /usr/local bin/protoc && \
@@ -28,22 +32,26 @@ RUN cargo chef cook --profile release-opt --recipe-path recipe.json
 ARG GIT_SHA
 ARG DOCKER_LABEL
 
+COPY Cargo.lock Cargo.lock
 COPY Cargo.toml Cargo.toml
 COPY rust-toolchain.toml rust-toolchain.toml
 COPY proto proto
 COPY benchmark benchmark
 COPY router router
+COPY backends backends
 COPY launcher launcher
-RUN cargo build --profile release-opt
+RUN cargo build --profile release-opt --frozen
 
 # Python builder
 # Adapted from: https://github.com/pytorch/pytorch/blob/master/Dockerfile
-FROM nvidia/cuda:12.1.0-devel-ubuntu22.04 AS pytorch-install
+FROM nvidia/cuda:12.4.1-devel-ubuntu22.04 AS pytorch-install
 
-ARG PYTORCH_VERSION=2.3.0
-ARG PYTHON_VERSION=3.10
+# NOTE: When updating PyTorch version, beware to remove `pip install nvidia-nccl-cu12==2.22.3` below in the Dockerfile. Context: https://github.com/huggingface/text-generation-inference/pull/2099
+ARG PYTORCH_VERSION=2.4.0
+
+ARG PYTHON_VERSION=3.11
 # Keep in sync with `server/pyproject.toml
-ARG CUDA_VERSION=12.1
+ARG CUDA_VERSION=12.4
 ARG MAMBA_VERSION=24.3.0-0
 ARG CUDA_CHANNEL=nvidia
 ARG INSTALL_CHANNEL=pytorch
@@ -84,6 +92,7 @@ RUN case ${TARGETPLATFORM} in \
 FROM pytorch-install AS kernel-builder
 
 ARG MAX_JOBS=8
+ENV TORCH_CUDA_ARCH_LIST="8.0;8.6;9.0+PTX"
 
 RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
         ninja-build cmake \
@@ -114,36 +123,29 @@ FROM kernel-builder AS exllama-kernels-builder
 WORKDIR /usr/src
 COPY server/exllama_kernels/ .
 
-RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" python setup.py build
+RUN python setup.py build
 
 # Build Transformers exllama kernels
 FROM kernel-builder AS exllamav2-kernels-builder
 WORKDIR /usr/src
-COPY server/exllamav2_kernels/ .
+COPY server/Makefile-exllamav2/ Makefile
 
 # Build specific version of transformers
-RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" python setup.py build
+RUN make build-exllamav2
 
 # Build Transformers awq kernels
 FROM kernel-builder AS awq-kernels-builder
 WORKDIR /usr/src
 COPY server/Makefile-awq Makefile
 # Build specific version of transformers
-RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" make build-awq
+RUN make build-awq
 
 # Build eetq kernels
 FROM kernel-builder AS eetq-kernels-builder
 WORKDIR /usr/src
 COPY server/Makefile-eetq Makefile
 # Build specific version of transformers
-RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" make build-eetq
-
-# Build marlin kernels
-FROM kernel-builder AS marlin-kernels-builder
-WORKDIR /usr/src
-COPY server/marlin/ .
-# Build specific version of transformers
-RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" python setup.py build
+RUN make build-eetq
 
 # Build Lorax Punica kernels
 FROM kernel-builder AS lorax-punica-builder
@@ -177,6 +179,12 @@ WORKDIR /usr/src
 COPY server/Makefile-selective-scan Makefile
 RUN make build-all
 
+# Build flashinfer
+FROM kernel-builder AS flashinfer-builder
+WORKDIR /usr/src
+COPY server/Makefile-flashinfer Makefile
+RUN make install-flashinfer
+
 # Text Generation Inference base image
 FROM nvidia/cuda:12.1.0-base-ubuntu22.04 AS base
 
@@ -185,7 +193,7 @@ ENV PATH=/opt/conda/bin:$PATH \
     CONDA_PREFIX=/opt/conda
 
 # Text Generation Inference base env
-ENV HUGGINGFACE_HUB_CACHE=/data \
+ENV HF_HOME=/data \
     HF_HUB_ENABLE_HF_TRANSFER=1 \
     PORT=80
 
@@ -203,33 +211,31 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-ins
 COPY --from=pytorch-install /opt/conda /opt/conda
 
 # Copy build artifacts from flash attention builder
-COPY --from=flash-att-builder /usr/src/flash-attention/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
-COPY --from=flash-att-builder /usr/src/flash-attention/csrc/layer_norm/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
-COPY --from=flash-att-builder /usr/src/flash-attention/csrc/rotary/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
+COPY --from=flash-att-builder /usr/src/flash-attention/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
+COPY --from=flash-att-builder /usr/src/flash-attention/csrc/layer_norm/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
+COPY --from=flash-att-builder /usr/src/flash-attention/csrc/rotary/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
 
 # Copy build artifacts from flash attention v2 builder
-COPY --from=flash-att-v2-builder /opt/conda/lib/python3.10/site-packages/flash_attn_2_cuda.cpython-310-x86_64-linux-gnu.so /opt/conda/lib/python3.10/site-packages
+COPY --from=flash-att-v2-builder /opt/conda/lib/python3.11/site-packages/flash_attn_2_cuda.cpython-311-x86_64-linux-gnu.so /opt/conda/lib/python3.11/site-packages
 
 # Copy build artifacts from custom kernels builder
-COPY --from=custom-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
+COPY --from=custom-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
 # Copy build artifacts from exllama kernels builder
-COPY --from=exllama-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
+COPY --from=exllama-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
 # Copy build artifacts from exllamav2 kernels builder
-COPY --from=exllamav2-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
+COPY --from=exllamav2-kernels-builder /usr/src/exllamav2/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
 # Copy build artifacts from awq kernels builder
-COPY --from=awq-kernels-builder /usr/src/llm-awq/awq/kernels/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
+COPY --from=awq-kernels-builder /usr/src/llm-awq/awq/kernels/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
 # Copy build artifacts from eetq kernels builder
-COPY --from=eetq-kernels-builder /usr/src/eetq/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
-# Copy build artifacts from marlin kernels builder
-COPY --from=marlin-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
-COPY --from=lorax-punica-builder /usr/src/lorax-punica/server/punica_kernels/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
-
-# Copy builds artifacts from vllm builder
-COPY --from=vllm-builder /usr/src/vllm/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
-
+COPY --from=eetq-kernels-builder /usr/src/eetq/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
+# Copy build artifacts from lorax punica kernels builder
+COPY --from=lorax-punica-builder /usr/src/lorax-punica/server/punica_kernels/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
+# Copy build artifacts from vllm builder
+COPY --from=vllm-builder /usr/src/vllm/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
 # Copy build artifacts from mamba builder
-COPY --from=mamba-builder /usr/src/mamba/build/lib.linux-x86_64-cpython-310/ /opt/conda/lib/python3.10/site-packages
-COPY --from=mamba-builder /usr/src/causal-conv1d/build/lib.linux-x86_64-cpython-310/ /opt/conda/lib/python3.10/site-packages
+COPY --from=mamba-builder /usr/src/mamba/build/lib.linux-x86_64-cpython-311/ /opt/conda/lib/python3.11/site-packages
+COPY --from=mamba-builder /usr/src/causal-conv1d/build/lib.linux-x86_64-cpython-311/ /opt/conda/lib/python3.11/site-packages
+COPY --from=flashinfer-builder /opt/conda/lib/python3.11/site-packages/flashinfer/ /opt/conda/lib/python3.11/site-packages/flashinfer/
 
 # Install flash-attention dependencies
 RUN pip install einops --no-cache-dir
@@ -241,7 +247,15 @@ COPY server/Makefile server/Makefile
 RUN cd server && \
     make gen-server && \
     pip install -r requirements_cuda.txt && \
-    pip install ".[bnb, accelerate, quantize, peft, outlines]" --no-cache-dir
+    pip install ".[bnb, accelerate, marlin, moe, quantize, peft, outlines]" --no-cache-dir && \
+    pip install nvidia-nccl-cu12==2.22.3
+
+ENV LD_PRELOAD=/opt/conda/lib/python3.11/site-packages/nvidia/nccl/lib/libnccl.so.2
+# Required to find libpython within the rust binaries
+ENV LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/opt/conda/lib/"
+# This is needed because exl2 tries to load flash-attn
+# And fails with our builds.
+ENV EXLLAMA_NO_FLASH_ATTN=1
 
 # Deps before the binaries
 # The binaries change on every build given we burn the SHA into them

Dockerfile.nix

+# Build the image and get out the docker file:
+#
+# docker build -t tgi-nix-builder -f Dockerfile.nix
+# docker run --log-driver=none tgi-nix-builder | docker load
+
+FROM nixos/nix:2.18.8 AS builder
+RUN echo "experimental-features = nix-command flakes" >> /etc/nix/nix.conf
+RUN nix profile install nixpkgs#cachix
+RUN cachix use text-generation-inference
+WORKDIR /root
+ADD . .
+RUN nix build .
+RUN mkdir /tmp/nix-store-closure
+RUN cp -R $(nix-store -qR result/) /tmp/nix-store-closure
+
+FROM ubuntu:24.04
+
+WORKDIR /app
+
+# Copy /nix/store
+COPY --from=builder /tmp/nix-store-closure /nix/store
+COPY --from=builder /root/result /app
+RUN ldconfig
+CMD ["ldconfig", "/app/bin/text-generation-launcher"]

Dockerfile_amd

 # Rust builder
-FROM lukemathwalker/cargo-chef:latest-rust-1.79 AS chef
+FROM lukemathwalker/cargo-chef:latest-rust-1.80.1 AS chef
 WORKDIR /usr/src
 
 ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
@@ -11,11 +11,14 @@ COPY rust-toolchain.toml rust-toolchain.toml
 COPY proto proto
 COPY benchmark benchmark
 COPY router router
+COPY backends backends
 COPY launcher launcher
 RUN cargo chef prepare --recipe-path recipe.json
 
 FROM chef AS builder
 
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
+    python3.11-dev
 RUN PROTOC_ZIP=protoc-21.12-linux-x86_64.zip && \
     curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v21.12/$PROTOC_ZIP && \
     unzip -o $PROTOC_ZIP -d /usr/local bin/protoc && \
@@ -28,16 +31,18 @@ RUN cargo chef cook --profile release-opt --recipe-path recipe.json
 ARG GIT_SHA
 ARG DOCKER_LABEL
 
+COPY Cargo.lock Cargo.lock
 COPY Cargo.toml Cargo.toml
 COPY rust-toolchain.toml rust-toolchain.toml
 COPY proto proto
 COPY benchmark benchmark
 COPY router router
+COPY backends backends
 COPY launcher launcher
-RUN cargo build --profile release-opt
+RUN cargo build --profile release-opt --frozen
 
 # Text Generation Inference base image for RoCm
-FROM rocm/dev-ubuntu-22.04:6.1.1_hip_update AS base
+FROM rocm/dev-ubuntu-22.04:6.2 AS base
 
 RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
     build-essential \
@@ -46,33 +51,34 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-ins
     curl \
     git \
     make \
+    libmsgpack-dev \
     libssl-dev \
+    llvm-dev \
     g++ \
     # Needed to build VLLM & flash.
     rocthrust-dev \
     hipsparse-dev \
     hipblas-dev \
-    hipblaslt-dev \
+    hipcub-dev \
     rocblas-dev \
     hiprand-dev \
+    hipfft-dev \
     rocrand-dev \
     miopen-hip-dev \
-    hipfft-dev \
-    hipcub-dev \
     hipsolver-dev \
     rccl-dev \
     cmake \
-    python3-dev && \
+    python3.11-venv && \
     rm -rf /var/lib/apt/lists/*
 
 # Keep in sync with `server/pyproject.toml
 ARG MAMBA_VERSION=23.1.0-1
-ARG PYTORCH_VERSION='2.3.0'
-ARG ROCM_VERSION='6.0.2'
-ARG PYTHON_VERSION='3.10.10'
+ARG PYTHON_VERSION='3.11.10'
 # Automatically set by buildx
 ARG TARGETPLATFORM
-ENV PATH /opt/conda/bin:$PATH
+ENV PATH=/opt/conda/bin:$PATH
+
+ARG PYTORCH_ROCM_ARCH="gfx90a;gfx942"
 
 # TGI seem to require libssl.so.1.1 instead of libssl.so.3 so we can't use ubuntu 22.04. Ubuntu 20.04 has python==3.8, and TGI requires python>=3.9, hence the need for miniconda.
 # Install mamba
@@ -87,42 +93,141 @@ RUN chmod +x ~/mambaforge.sh && \
     mamba init && \
     rm ~/mambaforge.sh
 
-# Install flash-attention, torch dependencies
-RUN pip install numpy einops ninja --no-cache-dir
-
-RUN conda install intel::mkl-static intel::mkl-include
-RUN pip uninstall -y triton && \
-    git clone --depth 1 --single-branch https://github.com/ROCm/triton.git && \
-    cd triton/python && \
-    pip install .
-
-RUN git clone --depth 1 --recursive --single-branch --branch 2.3-patched https://github.com/fxmarty/pytorch.git pytorch && cd pytorch && pip install -r requirements.txt --no-cache-dir
+# RUN conda install intel::mkl-static intel::mkl-include
+# Install pytorch
+# On arm64 we exit with an error code
+RUN case ${TARGETPLATFORM} in \
+         "linux/arm64")  exit 1 ;; \
+         *)              /opt/conda/bin/conda update -y conda &&  \
+                         /opt/conda/bin/conda install -y "python=${PYTHON_VERSION}" ;; \
+    esac && \
+    /opt/conda/bin/conda clean -ya
 
-ARG _GLIBCXX_USE_CXX11_ABI="1"
-ARG CMAKE_PREFIX_PATH="/opt/conda"
+# Install flash-attention, torch dependencies
+RUN python3 -m pip install --upgrade pip && pip install numpy einops ninja joblib msgpack cmake --no-cache-dir && rm -rf /var/lib/apt/lists/*
+
+RUN conda install mkl=2021
+ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/rocm/lib/:/opt/conda/lib/python3.11/site-packages/torch/lib:/opt/conda/lib/
+
+
+ARG COMMON_WORKDIR=/
+WORKDIR ${COMMON_WORKDIR}
+
+
+# Install HIPBLASLt
+FROM base AS build_hipblaslt
+ARG HIPBLASLT_BRANCH="e6da924"
+RUN git clone https://github.com/ROCm/hipBLASLt.git \
+    && cd hipBLASLt \
+    && git checkout ${HIPBLASLT_BRANCH} \
+    && SCCACHE_IDLE_TIMEOUT=1800 ./install.sh --architecture ${PYTORCH_ROCM_ARCH} --legacy_hipblas_direct \
+    && cd build/release \
+    && make package
+
+FROM scratch AS export_hipblaslt
+ARG COMMON_WORKDIR
+COPY --from=build_hipblaslt ${COMMON_WORKDIR}/hipBLASLt/build/release/*.deb /
+
+# RCCL build stages
+FROM base AS build_rccl
+ARG RCCL_BRANCH="rocm-6.2.0"
+RUN git clone https://github.com/ROCm/rccl \
+    && cd rccl \
+    && git checkout ${RCCL_BRANCH} \
+    && ./install.sh -p --amdgpu_targets ${PYTORCH_ROCM_ARCH}
+FROM scratch AS export_rccl
+ARG COMMON_WORKDIR
+COPY --from=build_rccl ${COMMON_WORKDIR}/rccl/build/release/*.deb /
+
+# Triton build stages
+FROM base AS build_triton
+ARG TRITON_BRANCH="e192dba"
+ARG TRITON_REPO="https://github.com/triton-lang/triton.git"
+RUN python3 -m pip install ninja cmake wheel pybind11 && git clone ${TRITON_REPO} \
+    && cd triton \
+    && git checkout ${TRITON_BRANCH} \
+    && cd python \
+    && python3 setup.py bdist_wheel --dist-dir=dist
+FROM scratch AS export_triton
+ARG COMMON_WORKDIR
+COPY --from=build_triton ${COMMON_WORKDIR}/triton/python/dist/*.whl /
+
+# # AMD-SMI build stages
+FROM base AS build_amdsmi
+RUN cd /opt/rocm/share/amd_smi \
+    && pip wheel . --wheel-dir=dist
+FROM scratch AS export_amdsmi
+COPY --from=build_amdsmi /opt/rocm/share/amd_smi/dist/*.whl /
+
+
+FROM base as build_pytorch
+
+RUN --mount=type=bind,from=export_hipblaslt,src=/,target=/install \
+    if ls /install/*.deb; then \
+        dpkg -i /install/*.deb \
+        && sed -i 's/, hipblaslt-dev \(.*\), hipcub-dev/, hipcub-dev/g' /var/lib/dpkg/status \
+        && sed -i 's/, hipblaslt \(.*\), hipfft/, hipfft/g' /var/lib/dpkg/status; \
+    fi
+
+ARG BUILD_ENVIRONMENT=pytorch-linux-jammy-rocm6.2-py3.11
 ARG PYTORCH_ROCM_ARCH="gfx90a;gfx942"
-ARG BUILD_CAFFE2="0" \
-    BUILD_CAFFE2_OPS="0" \
-    USE_CUDA="0" \
-    USE_ROCM="1" \
-    BUILD_TEST="0" \
-    USE_FBGEMM="0" \
-    USE_NNPACK="0" \
-    USE_QNNPACK="0" \
-    USE_XNNPACK="0" \
-    USE_FLASH_ATTENTION="1" \
-    USE_MEM_EFF_ATTENTION="0"
-
-RUN cd pytorch && python tools/amd_build/build_amd.py && python setup.py install
 
-# Set AS recommended: https://github.com/ROCm/triton/wiki/A-script-to-set-program-execution-environment-in-ROCm
-ENV HIP_FORCE_DEV_KERNARG=1
-
-# On MI250 and MI300, performances for flash with Triton FA are slightly better than CK.
-# However, Triton requires a tunning for each prompt length, which is prohibitive.
-ENV ROCM_USE_FLASH_ATTN_V2_TRITON=0
-
-FROM base AS kernel-builder
+# A commit to fix the output scaling factor issue in _scaled_mm
+# Not yet in 2.5.0-rc1
+ARG PYTORCH_BRANCH="cedc116"
+ARG PYTORCH_VISION_BRANCH="v0.19.1"
+ARG PYTORCH_REPO="https://github.com/ROCm/pytorch.git"
+
+RUN git clone ${PYTORCH_REPO} pytorch \
+    && cd pytorch && git checkout ${PYTORCH_BRANCH} && git submodule update --init --recursive \
+    && pip install -r requirements.txt --no-cache-dir  \
+    && python tools/amd_build/build_amd.py \
+    && CMAKE_PREFIX_PATH=$(python3 -c 'import sys; print(sys.prefix)') python3 setup.py bdist_wheel --dist-dir=dist
+FROM scratch as export_pytorch
+ARG COMMON_WORKDIR
+COPY --from=build_pytorch ${COMMON_WORKDIR}/pytorch/dist/*.whl /
+
+FROM base AS install_deps
+
+ARG COMMON_WORKDIR
+
+# Install hipblaslt
+RUN --mount=type=bind,from=export_hipblaslt,src=/,target=/install \
+    if ls /install/*.deb; then \
+        dpkg -i /install/*.deb \
+        && sed -i 's/, hipblaslt-dev \(.*\), hipcub-dev/, hipcub-dev/g' /var/lib/dpkg/status \
+        && sed -i 's/, hipblaslt \(.*\), hipfft/, hipfft/g' /var/lib/dpkg/status; \
+    fi
+
+RUN --mount=type=bind,from=export_rccl,src=/,target=/install \
+    if ls /install/*.deb; then \
+        dpkg -i /install/*.deb \
+        # RCCL needs to be installed twice
+        && dpkg -i /install/*.deb \
+        && sed -i 's/, rccl-dev \(.*\), rocalution/, rocalution/g' /var/lib/dpkg/status \
+        && sed -i 's/, rccl \(.*\), rocalution/, rocalution/g' /var/lib/dpkg/status; \
+    fi
+
+RUN --mount=type=bind,from=export_triton,src=/,target=/install \
+    if ls /install/*.whl; then \
+        # Preemptively uninstall to prevent pip same-version no-installs
+        pip uninstall -y triton \
+        && pip install /install/*.whl; \
+    fi
+
+RUN --mount=type=bind,from=export_amdsmi,src=/,target=/install \
+    # Preemptively uninstall to prevent pip same-version no-installs
+    pip uninstall -y amdsmi \
+    && pip install /install/*.whl;
+
+RUN --mount=type=bind,from=export_pytorch,src=/,target=/install \
+    if ls /install/*.whl; then \
+        # Preemptively uninstall to prevent pip same-version no-installs
+        pip uninstall -y torch torchvision \
+        && pip install /install/*.whl; \
+    fi
+
+FROM install_deps AS kernel-builder
 
 # # Build vllm kernels
 FROM kernel-builder AS vllm-builder
@@ -162,27 +267,27 @@ COPY server/exllamav2_kernels/ .
 
 RUN python setup.py build
 
-FROM base AS base-copy
+FROM install_deps AS base-copy
 
 # Text Generation Inference base env
-ENV HUGGINGFACE_HUB_CACHE=/data \
+ENV HF_HOME=/data \
     HF_HUB_ENABLE_HF_TRANSFER=1 \
     PORT=80
 
 # Copy builds artifacts from vllm builder
-COPY --from=vllm-builder /usr/src/vllm/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
+COPY --from=vllm-builder /usr/src/vllm/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
 
 # Copy build artifacts from flash attention v2 builder
-COPY --from=flash-att-v2-builder /usr/src/flash-attention-v2/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
+COPY --from=flash-att-v2-builder /usr/src/flash-attention-v2/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
 
 # Copy build artifacts from custom kernels builder
-COPY --from=custom-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
+COPY --from=custom-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
 
 # Copy build artifacts from exllama kernels builder
-COPY --from=exllama-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
+COPY --from=exllama-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
 
 # Copy build artifacts from exllamav2 kernels builder
-COPY --from=exllamav2-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-310 /opt/conda/lib/python3.10/site-packages
+COPY --from=exllamav2-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
 
 # Install server
 COPY proto proto
@@ -199,6 +304,7 @@ COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/l
 COPY --from=builder /usr/src/target/release-opt/text-generation-router /usr/local/bin/text-generation-router
 # Install launcher
 COPY --from=builder /usr/src/target/release-opt/text-generation-launcher /usr/local/bin/text-generation-launcher
+ENV LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/opt/conda/lib/"
 
 # AWS Sagemaker compatible image
 FROM base AS sagemaker
@@ -211,6 +317,20 @@ ENTRYPOINT ["./entrypoint.sh"]
 # Final image
 FROM base-copy
 
+# Set AS recommended: https://github.com/ROCm/triton/wiki/A-script-to-set-program-execution-environment-in-ROCm
+ENV HIP_FORCE_DEV_KERNARG=1
+
+# On MI250 and MI300, performances for flash with Triton FA are slightly better than CK.
+# However, Triton requires a tunning for each prompt length, which is prohibitive.
+ENV ROCM_USE_FLASH_ATTN_V2_TRITON=0
+ENV ROCM_USE_CUSTOM_PAGED_ATTN=1
+ENV PYTORCH_TUNABLEOP_TUNING_AFTER_WARMUP=0
+ENV VLLM_MOE_PADDING=0
+ENV ATTENTION=paged
+ENV PREFIX_CACHING=0
+ENV PREFILL_CHUNKING=0
+ENV ROCM_USE_SKINNY_GEMM=1
+
 COPY ./tgi-entrypoint.sh /tgi-entrypoint.sh
 RUN chmod +x /tgi-entrypoint.sh
 

Dockerfile_dcu

-# Rust builder
-FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk24.04-py310 as chef
-RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
-ENV PATH /root/.cargo/bin:$PATH
-RUN cargo install cargo-chef
-WORKDIR /usr/src
-
-ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
-
-FROM chef as planner
-COPY Cargo.toml Cargo.toml
-COPY Cargo.lock Cargo.lock
-COPY rust-toolchain.toml rust-toolchain.toml
-COPY proto proto
-COPY benchmark benchmark
-COPY router router
-COPY launcher launcher
-RUN cargo chef prepare --recipe-path recipe.json
-
-FROM chef AS builder
-
-ARG GIT_SHA
-ARG DOCKER_LABEL
-
-RUN PROTOC_ZIP=protoc-21.12-linux-x86_64.zip && \
-    curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v21.12/$PROTOC_ZIP && \
-    unzip -o $PROTOC_ZIP -d /usr/local bin/protoc && \
-    unzip -o $PROTOC_ZIP -d /usr/local 'include/*' && \
-    rm -f $PROTOC_ZIP
-COPY --from=planner /usr/src/recipe.json recipe.json
-RUN cargo chef cook --release --recipe-path recipe.json
-
-COPY Cargo.toml Cargo.toml
-COPY Cargo.lock Cargo.lock
-COPY rust-toolchain.toml rust-toolchain.toml
-COPY proto proto
-COPY benchmark benchmark
-COPY router router
-COPY launcher launcher
-RUN cargo build --release
-
-# Text Generation Inference base image for RoCm
-FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk24.04-py310 as base
-# Need hyhal while compiling
-WORKDIR /opt
-RUN wget https://cancon.hpccube.com:65024/directlink/1/DTK-23.10.1/hyhal.tar.gz && \
-    tar -xzf hyhal.tar.gz -C /opt
-
-ENV LD_LIBRARY_PATH /opt/hyhal/lib:/opt/hyhal/lib64:$LD_LIBRARY_PATH
-ENV PYTHONPATH /usr/local/lib/python3.10/site-packages:$PYTHONPATH
-
-FROM base AS kernel-builder
-
-# Build vllm kernels
-FROM kernel-builder AS vllm-builder
-WORKDIR /usr/src
-COPY server/vllm/ . 
-
-# Build specific version of vllm
-RUN python setup.py build
-
-# Build Transformers CUDA kernels (gpt-neox and bloom)
-FROM kernel-builder as custom-kernels-builder
-WORKDIR /usr/src
-COPY server/custom_kernels/ .
-RUN python setup.py build
-
-# Build exllama kernels
-FROM kernel-builder as exllama-kernels-builder
-WORKDIR /usr/src
-COPY server/exllama_kernels/ .
-
-RUN python setup.py build
-
-# Build exllama v2 kernels
-FROM kernel-builder as exllamav2-kernels-builder
-WORKDIR /usr/src
-COPY server/exllamav2_kernels/ .
-
-RUN python setup.py build
-
-FROM base as base-copy
-
-# uninstall exist vllm in base docker image
-RUN pip uninstall -y vllm
-
-# Copy builds artifacts from vllm builder
-COPY --from=vllm-builder /usr/src/build/lib.linux-x86_64-cpython-310 /usr/local/lib/python3.10/site-packages
-
-# Copy build artifacts from custom kernels builder
-COPY --from=custom-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-310 /usr/local/lib/python3.10/site-packages
-
-# Copy build artifacts from exllama kernels builder
-COPY --from=exllama-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-310 /usr/local/lib/python3.10/site-packages
-
-# Copy build artifacts from exllamav2 kernels builder
-COPY --from=exllamav2-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-310 /usr/local/lib/python3.10/site-packages
-
-# Install server
-RUN pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
-COPY proto proto
-COPY server server
-COPY server/Makefile server/Makefile
-RUN cd server && \
-    make gen-server && \
-    pip install -r requirements_rocm.txt && \
-    pip install ".[accelerate, peft, outlines]" --no-cache-dir
-
-# Install benchmarker
-COPY --from=builder /usr/src/target/release/text-generation-benchmark /usr/local/bin/text-generation-benchmark
-# Install router
-COPY --from=builder /usr/src/target/release/text-generation-router /usr/local/bin/text-generation-router
-# Install launcher
-COPY --from=builder /usr/src/target/release/text-generation-launcher /usr/local/bin/text-generation-launcher
-
-#Remove default hyhal
-RUN rm -rf /opt/hyhal /opt/hyhal.tar.gz
-
-# AWS Sagemaker compatible image
-# FROM base-copy as sagemaker
-# COPY sagemaker-entrypoint.sh entrypoint.sh
-# RUN chmod +x entrypoint.sh
-
-# ENTRYPOINT ["./entrypoint.sh"]
-
-# # Final image
-# FROM base-copy
-
-# ENTRYPOINT ["text-generation-launcher"]
-# CMD ["--json-output"]

Dockerfile_intel

 ARG PLATFORM=xpu
 
-FROM lukemathwalker/cargo-chef:latest-rust-1.79 AS chef
+FROM lukemathwalker/cargo-chef:latest-rust-1.80.1 AS chef
 WORKDIR /usr/src
 
 ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
@@ -12,11 +12,14 @@ COPY rust-toolchain.toml rust-toolchain.toml
 COPY proto proto
 COPY benchmark benchmark
 COPY router router
+COPY backends backends
 COPY launcher launcher
 RUN cargo chef prepare --recipe-path recipe.json
 
 FROM chef AS builder
 
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
+    python3.11-dev
 RUN PROTOC_ZIP=protoc-21.12-linux-x86_64.zip && \
     curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v21.12/$PROTOC_ZIP && \
     unzip -o $PROTOC_ZIP -d /usr/local bin/protoc && \
@@ -29,20 +32,48 @@ RUN cargo chef cook --profile release-opt --recipe-path recipe.json
 ARG GIT_SHA
 ARG DOCKER_LABEL
 
+COPY Cargo.lock Cargo.lock
 COPY Cargo.toml Cargo.toml
 COPY rust-toolchain.toml rust-toolchain.toml
 COPY proto proto
 COPY benchmark benchmark
 COPY router router
+COPY backends backends
 COPY launcher launcher
-RUN cargo build --profile release-opt
+RUN cargo build --profile release-opt --frozen
 
 
 # Text Generation Inference base image for Intel
 
-FROM intel/intel-extension-for-pytorch:2.1.30-xpu AS xpu
+FROM intel/intel-extension-for-pytorch:2.3.110-xpu AS xpu
 
 USER root
+
+ARG MAMBA_VERSION=23.1.0-1
+ARG PYTHON_VERSION='3.11.10'
+# Automatically set by buildx
+ARG TARGETPLATFORM
+ENV PATH=/opt/conda/bin:$PATH
+
+# TGI seem to require libssl.so.1.1 instead of libssl.so.3 so we can't use ubuntu 22.04. Ubuntu 20.04 has python==3.8, and TGI requires python>=3.9, hence the need for miniconda.
+# Install mamba
+# translating Docker's TARGETPLATFORM into mamba arches
+RUN case ${TARGETPLATFORM} in \
+         "linux/arm64")  MAMBA_ARCH=aarch64  ;; \
+         *)              MAMBA_ARCH=x86_64   ;; \
+    esac && \
+    curl -fsSL -v -o ~/mambaforge.sh -O  "https://github.com/conda-forge/miniforge/releases/download/${MAMBA_VERSION}/Mambaforge-${MAMBA_VERSION}-Linux-${MAMBA_ARCH}.sh"
+RUN chmod +x ~/mambaforge.sh && \
+    bash ~/mambaforge.sh -b -p /opt/conda && \
+    rm ~/mambaforge.sh
+
+RUN case ${TARGETPLATFORM} in \
+         "linux/arm64")  exit 1 ;; \
+         *)              /opt/conda/bin/conda update -y conda &&  \
+                         /opt/conda/bin/conda install -y "python=${PYTHON_VERSION}" ;; \
+    esac && \
+    /opt/conda/bin/conda clean -ya
+
 # libssl.so.1.1 is not installed on Ubuntu 22.04 by default, install it
 RUN wget http://nz2.archive.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2_amd64.deb && \
     dpkg -i ./libssl1.1_1.1.1f-1ubuntu2_amd64.deb
@@ -52,18 +83,16 @@ RUN wget -qO - https://repositories.intel.com/gpu/intel-graphics.key | gpg --dea
 RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB \
 | gpg --dearmor | tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null && echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list
 
-RUN apt-get update && apt install -y intel-basekit xpu-smi cmake python3-dev ninja-build pciutils
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt install -y intel-basekit xpu-smi cmake ninja-build pciutils
 
 # Text Generation Inference base env
-ENV HUGGINGFACE_HUB_CACHE=/data \
+ENV HF_HOME=/data \
     HF_HUB_ENABLE_HF_TRANSFER=1 \
     PORT=80
 
 
 WORKDIR /usr/src
-RUN wget https://intel-extension-for-pytorch.s3.amazonaws.com/ipex_dev/xpu/torch-2.1.0.post1%2Bcxx11.abi-cp310-cp310-linux_x86_64.whl && pip install torch-2.1.0.post1+cxx11.abi-cp310-cp310-linux_x86_64.whl
-RUN pip install https://github.com/intel/intel-xpu-backend-for-triton/releases/download/v2.1.0/triton-2.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
-RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout -b distributed origin/dev/distributed
+RUN pip install torch==2.3.1+cxx11.abi torchvision==0.18.1+cxx11.abi torchaudio==2.3.1+cxx11.abi intel-extension-for-pytorch==2.3.110+xpu oneccl_bind_pt==2.3.100+xpu --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ --no-cache-dir
 
 # Install server
 COPY proto proto
@@ -78,13 +107,13 @@ ENV CCL_ROOT=/opt/intel/oneapi/ccl/latest
 ENV I_MPI_ROOT=/opt/intel/oneapi/mpi/latest
 ENV FI_PROVIDER_PATH=/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/lib/prov:/usr/lib/x86_64-linux-gnu/libfabric
 ENV LIBRARY_PATH=/opt/intel/oneapi/mpi/latest/lib:/opt/intel/oneapi/ccl/latest/lib/:/opt/intel/oneapi/mkl/latest/lib/:/opt/intel/oneapi/compiler/latest/lib
-ENV LD_LIBRARY_PATH=/opt/intel/oneapi/ccl/latest/lib/:/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/lib:/opt/intel/oneapi/mpi/latest/lib:/opt/intel/oneapi/mkl/latest/lib:/opt/intel/oneapi/compiler/latest/opt/compiler/lib:/opt/intel/oneapi/compiler/latest/lib:/opt/intel/oneapi/lib:/opt/intel/oneapi/lib/intel64:
-ENV PATH=/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/bin:/opt/intel/oneapi/mpi/latest/bin:/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/bin:/opt/intel/oneapi/mkl/latest/bin/:/opt/intel/oneapi/compiler/latest/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
+ENV LD_LIBRARY_PATH=/opt/intel/oneapi/ccl/latest/lib/:/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/lib:/opt/intel/oneapi/mpi/latest/lib:/opt/intel/oneapi/mkl/latest/lib:/opt/intel/oneapi/compiler/latest/opt/compiler/lib:/opt/intel/oneapi/compiler/latest/lib:/opt/intel/oneapi/lib:/opt/intel/oneapi/lib/intel64:/opt/conda/lib
+ENV PATH=/opt/conda/bin:/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/bin:/opt/intel/oneapi/mpi/latest/bin:/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/bin:/opt/intel/oneapi/mkl/latest/bin/:/opt/intel/oneapi/compiler/latest/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
 ENV CCL_ZE_IPC_EXCHANGE=sockets
 ENV CMAKE_PREFIX_PATH=/opt/intel/oneapi/mkl/latest/lib/cmake:/opt/intel/oneapi/compiler/latest
 ENV CPATH=/opt/intel/oneapi/mpi/latest/include:/opt/intel/oneapi/ccl/latest/include:/opt/intel/oneapi/mkl/latest/include
-
-RUN pip uninstall -y intel-extension-for-pytorch && cd intel-extension-for-pytorch && git submodule update --init --recursive && USE_AOT_DEVLIST='pvc' BUILD_SEPARATE_OPS=OFF BUILD_WITH_CPU=OFF USE_XETLA=ON python setup.py install && rm -rf /usr/src/intel-extension-for-pytorch
+ENV TORCH_LLM_ALLREDUCE=1
+ENV CCL_TOPO_FABRIC_VERTEX_CONNECTION_CHECK=0
 
 # Install benchmarker
 COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark
@@ -101,17 +130,28 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-ins
     curl \
     ca-certificates \
     make \
-    g++ \
+    g++-12 \
+    gcc-12 \
     git \
     wget \
-    cmake
+    cmake \
+    libnuma-dev
+
+RUN update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-12 12
+RUN update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 12
+RUN update-alternatives --install /usr/bin/cc cc /usr/bin/gcc 30
+RUN update-alternatives --set cc /usr/bin/gcc
+
+RUN update-alternatives --install /usr/bin/c++ c++ /usr/bin/g++ 30
+RUN update-alternatives --set c++ /usr/bin/g++
+
 
 ENV HUGGINGFACE_HUB_CACHE=/data \
     HF_HUB_ENABLE_HF_TRANSFER=1 \
     PORT=80
 
 ARG MAMBA_VERSION=23.1.0-1
-ARG PYTHON_VERSION='3.10.10'
+ARG PYTHON_VERSION='3.11.10'
 # Automatically set by buildx
 ARG TARGETPLATFORM
 ENV PATH /opt/conda/bin:$PATH
@@ -128,33 +168,37 @@ RUN chmod +x ~/mambaforge.sh && \
     bash ~/mambaforge.sh -b -p /opt/conda && \
     rm ~/mambaforge.sh
 
+RUN case ${TARGETPLATFORM} in \
+         "linux/arm64")  exit 1 ;; \
+         *)              /opt/conda/bin/conda update -y conda &&  \
+                         /opt/conda/bin/conda install -y "python=${PYTHON_VERSION}" ;; \
+    esac && \
+    /opt/conda/bin/conda clean -ya
+
 RUN conda install -c conda-forge gperftools mkl
 
-RUN pip install https://download.pytorch.org/whl/nightly/cpu/torch-2.4.0.dev20240612%2Bcpu-cp310-cp310-linux_x86_64.whl
-RUN pip install https://download.pytorch.org/whl/nightly/cpu/torchvision-0.19.0.dev20240612%2Bcpu-cp310-cp310-linux_x86_64.whl
-RUN pip install https://download.pytorch.org/whl/nightly/cpu/torchaudio-2.4.0.dev20240612%2Bcpu-cp310-cp310-linux_x86_64.whl
-RUN pip install triton
 
-WORKDIR /usr/src
+RUN pip install https://download.pytorch.org/whl/nightly/cpu/torch-2.5.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl
+RUN pip install https://download.pytorch.org/whl/nightly/cpu/torchvision-0.20.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl
+RUN pip install https://download.pytorch.org/whl/nightly/cpu/torchaudio-2.4.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl
 
-RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout eda7a7c42df6f9a64e0de9c2b69304ee02f2c32a
+RUN pip install triton py-libnuma
+
+WORKDIR /usr/src
 
-RUN git clone https://github.com/intel/torch-ccl.git && cd torch-ccl && git checkout ccl_torch_dev_0131
+RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout f86e93e4890dc2c989024d148d415c9aa8a1649f
+RUN git clone https://github.com/intel/torch-ccl.git && cd torch-ccl && git checkout v2.4.0+cpu+rc0
 
 RUN cd intel-extension-for-pytorch && git submodule sync && git submodule update --init --recursive && python setup.py install
 
 RUN cd torch-ccl && git submodule sync && git submodule update --init --recursive && pip install .
 
-ENV LD_PRELOAD=/opt/conda/lib/libtcmalloc.so:/opt/conda/lib/libiomp5.so
-ENV CCL_ROOT=/opt/conda/lib/python3.10/site-packages/oneccl_bindings_for_pytorch
-ENV I_MPI_ROOT=/opt/conda/lib/python3.10/site-packages/oneccl_bindings_for_pytorch
-ENV FI_PROVIDER_PATH=/opt/conda/lib/python3.10/site-packages/oneccl_bindings_for_pytorch/opt/mpi/libfabric/lib/prov:/usr/lib64/libfabric
-ENV LD_LIBRARY_PATH=/opt/conda/lib/python3.10/site-packages/oneccl_bindings_for_pytorch/opt/mpi/libfabric/lib:/opt/conda/lib/python3.10/site-packages/oneccl_bindings_for_pytorch/lib
-ENV KMP_BLOCKTIME=1
-ENV KMP_TPAUSE=0
-ENV KMP_FORKJOIN_BARRIER_PATTERN=dist,dist
-ENV KMP_PLAIN_BARRIER_PATTERN=dist,dist
-ENV KMP_REDUCTION_BARRIER_PATTERN=dist,dist
+ENV LD_PRELOAD=/opt/conda/lib/libtcmalloc.so
+ENV CCL_ROOT=/opt/conda/lib/python3.11/site-packages/oneccl_bindings_for_pytorch
+ENV I_MPI_ROOT=/opt/conda/lib/python3.11/site-packages/oneccl_bindings_for_pytorch
+ENV FI_PROVIDER_PATH=/opt/conda/lib/python3.11/site-packages/oneccl_bindings_for_pytorch/opt/mpi/libfabric/lib/prov:/usr/lib64/libfabric
+ENV LD_LIBRARY_PATH=/opt/conda/lib/python3.11/site-packages/oneccl_bindings_for_pytorch/opt/mpi/libfabric/lib:/opt/conda/lib/python3.11/site-packages/oneccl_bindings_for_pytorch/lib
+ENV LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/opt/conda/lib/"
 
 # Install server
 COPY proto proto
@@ -173,5 +217,9 @@ COPY --from=builder /usr/src/target/release-opt/text-generation-router /usr/loca
 COPY --from=builder /usr/src/target/release-opt/text-generation-launcher /usr/local/bin/text-generation-launcher
 
 FROM ${PLATFORM} AS final
+ENV ATTENTION=paged
+ENV PREFIX_CACHING=0
+ENV PREFILL_CHUNKING=0
+ENV CUDA_GRAPHS=0
 ENTRYPOINT ["text-generation-launcher"]
 CMD ["--json-output"]

Dockerfile_trtllm

+ARG CUDA_ARCH_LIST="75-real;80-real;86-real;89-real;90-real"
+ARG OMPI_VERSION="4.1.6"
+
+# Build dependencies resolver stage
+FROM lukemathwalker/cargo-chef:latest AS chef
+WORKDIR /usr/src/text-generation-inference/backends/trtllm
+
+FROM chef AS planner
+COPY . .
+RUN cargo chef prepare --recipe-path recipe.json
+
+# CUDA dependent dependencies resolver stage
+FROM nvidia/cuda:12.6.1-cudnn-devel-ubuntu22.04 AS cuda-builder
+
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    --mount=type=cache,target=/var/lib/apt,sharing=locked \
+    apt update && apt install -y \
+    build-essential \
+    cmake \
+    curl \
+    gcc  \
+    g++ \
+    git \
+    git-lfs \
+    libssl-dev \
+    ninja-build \
+    pkg-config \
+    python3 \
+    python3-dev \
+    python3-setuptools \
+    tar \
+    wget
+
+ENV TGI_INSTALL_PREFIX=/usr/local/tgi
+ENV TENSORRT_INSTALL_PREFIX=/usr/local/tensorrt
+
+# Install OpenMPI
+FROM cuda-builder AS mpi-builder
+ARG OMPI_VERSION
+
+ENV OMPI_TARBALL_FILENAME="openmpi-$OMPI_VERSION.tar.bz2"
+RUN wget "https://download.open-mpi.org/release/open-mpi/v4.1/$OMPI_TARBALL_FILENAME" -P /opt/src && \
+    mkdir /usr/src/mpi && \
+    tar -xf "/opt/src/$OMPI_TARBALL_FILENAME" -C /usr/src/mpi --strip-components=1 && \
+    cd /usr/src/mpi && \
+    ./configure --prefix=/usr/local/mpi --with-cuda=/usr/local/cuda --with-slurm && \
+    make -j all && \
+    make install && \
+    rm -rf "/opt/src/$OMPI_TARBALL_FILENAME"
+
+# Install TensorRT
+FROM cuda-builder AS trt-builder
+COPY backends/trtllm/scripts/install_tensorrt.sh /opt/install_tensorrt.sh
+RUN chmod +x /opt/install_tensorrt.sh && \
+    /opt/install_tensorrt.sh
+
+# Build Backend
+FROM cuda-builder AS tgi-builder
+WORKDIR /usr/src/text-generation-inference
+
+# Install Rust
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | bash -s -- -y && \
+    chmod -R a+w /root/.rustup && \
+    chmod -R a+w /root/.cargo
+
+ENV PATH="/root/.cargo/bin:$PATH"
+RUN cargo install cargo-chef
+
+# Cache dependencies
+COPY --from=planner /usr/src/text-generation-inference/backends/trtllm/recipe.json .
+RUN cargo chef cook --release --recipe-path recipe.json
+
+# Build actual TGI
+ARG CUDA_ARCH_LIST
+ENV CMAKE_PREFIX_PATH="/usr/local/mpi:/usr/local/tensorrt:$CMAKE_PREFIX_PATH"
+ENV LD_LIBRARY_PATH="/usr/local/mpi/lib:$LD_LIBRARY_PATH"
+ENV PKG_CONFIG_PATH="/usr/local/mpi/lib/pkgconfig:$PKG_CONFIG_PATH"
+
+COPY . .
+COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
+COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi
+RUN mkdir $TGI_INSTALL_PREFIX && mkdir "$TGI_INSTALL_PREFIX/include" && mkdir "$TGI_INSTALL_PREFIX/lib" && \
+    cd backends/trtllm && \
+    CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --release
+
+FROM nvidia/cuda:12.6.1-cudnn-runtime-ubuntu22.04 AS runtime
+RUN apt update && apt install -y python3-minimal python3-dev python3-pip && \
+    rm -rf /var/lib/{apt,dpkg,cache,log}/ && \
+    python3 -m pip install transformers tokenizers
+
+WORKDIR /usr/local/tgi/bin
+
+ENV LD_LIBRARY_PATH="/usr/local/tgi/lib:/usr/local/mpi/lib:/usr/local/tensorrt/lib:/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH"
+ENV TOKENIZERS_PARALLELISM=false
+ENV OMPI_MCA_plm_rsh_agent=""
+
+COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi
+COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
+COPY --from=tgi-builder /usr/local/tgi /usr/local/tgi
+COPY --from=tgi-builder /usr/src/text-generation-inference/target/release/text-generation-backends-trtllm /usr/local/tgi/bin/text-generation-launcher
+
+FROM runtime
+
+LABEL co.huggingface.vendor="Hugging Face Inc."
+LABEL org.opencontainers.image.authors="hardware@hf.co"
+
+ENTRYPOINT ["./text-generation-launcher"]
+CMD ["--executor-worker", "/usr/local/tgi/bin/executorWorker"]

Makefile

@@ -5,13 +5,13 @@ install-server-cpu:
 	cd server && make install-server
 
 install-router:
-	cd router && cargo install --path . --debug
+	cargo install --path backends/v3/
 
 install-launcher:
-	cd launcher && cargo install --path .
+	cargo install --path launcher/
 
 install-benchmark:
-	cd benchmark && cargo install --path .
+	cargo install --path benchmark/
 
 install: install-server install-router install-launcher
 

README.md

- <div align="center"><strong>Text Generation Inference </strong></div>
+<div align="center">
 
-## 简介
-Text Generation Inference（TGI）是一个用 Rust 和 Python 编写的框架，用于部署和提供LLM模型的推理服务。TGI为很多大模型提供了高性能的推理服务，如LLama,Falcon,BLOOM,Baichuan,Qwen等。
+<a href="https://www.youtube.com/watch?v=jlMAX2Oaht0">
+  <img width=560 width=315 alt="Making TGI deployment optimal" src="https://huggingface.co/datasets/Narsil/tgi_assets/resolve/main/thumbnail.png">
+</a>
 
-## 支持模型结构列表
-|     模型      | 模型并行 | FP16 |
-| :----------: | :------: | :--: |
-|    LLaMA          |   Yes    | Yes  |
-|    LLaMA-2        |   Yes    | Yes  |
-|    LLaMA-2-GPTQ        |   Yes    | Yes  |
-|    LLaMA-3        |   Yes    | Yes  |
-|    Codellama      |   Yes    | Yes  |
-|    QWen2          |   Yes    | Yes  |
-|    QWen2-GPTQ        |   Yes    | Yes  |
-|    Baichuan-7B    |   Yes    | Yes  |
-|    Baichuan2-7B   |   Yes    | Yes  |
-|    Baichuan2-13B  |   Yes    | Yes  |
+# Text Generation Inference
 
+<a href="https://github.com/huggingface/text-generation-inference">
+  <img alt="GitHub Repo stars" src="https://img.shields.io/github/stars/huggingface/text-generation-inference?style=social">
+</a>
+<a href="https://huggingface.github.io/text-generation-inference">
+  <img alt="Swagger API documentation" src="https://img.shields.io/badge/API-Swagger-informational">
+</a>
 
-## 环境要求
-+ Python 3.10
-+ DTK 24.04.2
-+ torch 2.1.0
+A Rust, Python and gRPC server for text generation inference. Used in production at [Hugging Face](https://huggingface.co)
+to power Hugging Chat, the Inference API and Inference Endpoint.
 
-### 使用源码编译方式安装
+</div>
 
-#### 编译环境准备
+## Table of contents
 
-有两种方式安装准备环境
-##### 方式一:
+  - [Get Started](#get-started)
+    - [Docker](#docker)
+    - [API documentation](#api-documentation)
+    - [Using a private or gated model](#using-a-private-or-gated-model)
+    - [A note on Shared Memory (shm)](#a-note-on-shared-memory-shm)
+    - [Distributed Tracing](#distributed-tracing)
+    - [Architecture](#architecture)
+    - [Local install](#local-install)
+  - [Optimized architectures](#optimized-architectures)
+  - [Run locally](#run-locally)
+    - [Run](#run)
+    - [Quantization](#quantization)
+  - [Develop](#develop)
+  - [Testing](#testing)
 
-### **TODO**
+Text Generation Inference (TGI) is a toolkit for deploying and serving Large Language Models (LLMs). TGI enables high-performance text generation for the most popular open-source LLMs, including Llama, Falcon, StarCoder, BLOOM, GPT-NeoX, and [more](https://huggingface.co/docs/text-generation-inference/supported_models). TGI implements many features, such as:
 
-##### 方式二：
+- Simple launcher to serve most popular LLMs
+- Production ready (distributed tracing with Open Telemetry, Prometheus metrics)
+- Tensor Parallelism for faster inference on multiple GPUs
+- Token streaming using Server-Sent Events (SSE)
+- Continuous batching of incoming requests for increased total throughput
+- [Messages API](https://huggingface.co/docs/text-generation-inference/en/messages_api) compatible with Open AI Chat Completion API
+- Optimized transformers code for inference using [Flash Attention](https://github.com/HazyResearch/flash-attention) and [Paged Attention](https://github.com/vllm-project/vllm) on the most popular architectures
+- Quantization with :
+  - [bitsandbytes](https://github.com/TimDettmers/bitsandbytes)
+  - [GPT-Q](https://arxiv.org/abs/2210.17323)
+  - [EETQ](https://github.com/NetEase-FuXi/EETQ)
+  - [AWQ](https://github.com/casper-hansen/AutoAWQ)
+  - [Marlin](https://github.com/IST-DASLab/marlin)
+  - [fp8](https://developer.nvidia.com/blog/nvidia-arm-and-intel-publish-fp8-specification-for-standardization-as-an-interchange-format-for-ai/)
+- [Safetensors](https://github.com/huggingface/safetensors) weight loading
+- Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226)
+- Logits warper (temperature scaling, top-p, top-k, repetition penalty, more details see [transformers.LogitsProcessor](https://huggingface.co/docs/transformers/internal/generation_utils#transformers.LogitsProcessor))
+- Stop sequences
+- Log probabilities
+- [Speculation](https://huggingface.co/docs/text-generation-inference/conceptual/speculation) ~2x latency
+- [Guidance/JSON](https://huggingface.co/docs/text-generation-inference/conceptual/guidance). Specify output format to speed up inference and make sure the output is valid according to some specs..
+- Custom Prompt Generation: Easily generate text by providing custom prompts to guide the model's output
+- Fine-tuning Support: Utilize fine-tuned models for specific tasks to achieve higher accuracy and performance
 
-基于光源pytorch2.1.0基础镜像环境：镜像下载地址：[https://sourcefind.cn/#/image/dcu/pytorch](https://sourcefind.cn/#/image/dcu/pytorch)，根据pytorch2.1.0、python、dtk及系统下载对应的镜像版本。pytorch2.1.0镜像里已经安装了trition,flash-attn
+### Hardware support
+
+- [Nvidia](https://github.com/huggingface/text-generation-inference/pkgs/container/text-generation-inference)
+- [AMD](https://github.com/huggingface/text-generation-inference/pkgs/container/text-generation-inference) (-rocm)
+- [Inferentia](https://github.com/huggingface/optimum-neuron/tree/main/text-generation-inference)
+- [Intel GPU](https://github.com/huggingface/text-generation-inference/pull/1475)
+- [Gaudi](https://github.com/huggingface/tgi-gaudi)
+- [Google TPU](https://huggingface.co/docs/optimum-tpu/howto/serving)
+
+
+## Get Started
+
+### Docker
+
+For a detailed starting guide, please see the [Quick Tour](https://huggingface.co/docs/text-generation-inference/quicktour). The easiest way of getting started is using the official Docker container:
+
+```shell
+model=HuggingFaceH4/zephyr-7b-beta
+# share a volume with the Docker container to avoid downloading weights every run
+volume=$PWD/data
+
+docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data \
+    ghcr.io/huggingface/text-generation-inference:2.4.0 --model-id $model
+```
+
+And then you can make requests like
+
+```bash
+curl 127.0.0.1:8080/generate_stream \
+    -X POST \
+    -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":20}}' \
+    -H 'Content-Type: application/json'
+```
+
+You can also use [TGI's Messages API](https://huggingface.co/docs/text-generation-inference/en/messages_api) to obtain Open AI Chat Completion API compatible responses.
+
+```bash
+curl localhost:8080/v1/chat/completions \
+    -X POST \
+    -d '{
+  "model": "tgi",
+  "messages": [
+    {
+      "role": "system",
+      "content": "You are a helpful assistant."
+    },
+    {
+      "role": "user",
+      "content": "What is deep learning?"
+    }
+  ],
+  "stream": true,
+  "max_tokens": 20
+}' \
+    -H 'Content-Type: application/json'
+```
+
+**Note:** To use NVIDIA GPUs, you need to install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html). We also recommend using NVIDIA drivers with CUDA version 12.2 or higher. For running the Docker container on a machine with no GPUs or CUDA support, it is enough to remove the `--gpus all` flag and add `--disable-custom-kernels`, please note CPU is not the intended platform for this project, so performance might be subpar.
+
+**Note:** TGI supports AMD Instinct MI210 and MI250 GPUs. Details can be found in the [Supported Hardware documentation](https://huggingface.co/docs/text-generation-inference/supported_models#supported-hardware). To use AMD GPUs, please use `docker run --device /dev/kfd --device /dev/dri --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.4.0-rocm --model-id $model` instead of the command above.
+
+To see all options to serve your models (in the [code](https://github.com/huggingface/text-generation-inference/blob/main/launcher/src/main.rs) or in the cli):
+```
+text-generation-launcher --help
+```
+
+### API documentation
+
+You can consult the OpenAPI documentation of the `text-generation-inference` REST API using the `/docs` route.
+The Swagger UI is also available at: [https://huggingface.github.io/text-generation-inference](https://huggingface.github.io/text-generation-inference).
+
+### Using a private or gated model
+
+You have the option to utilize the `HF_TOKEN` environment variable for configuring the token employed by
+`text-generation-inference`. This allows you to gain access to protected resources.
+
+For example, if you want to serve the gated Llama V2 model variants:
+
+1. Go to https://huggingface.co/settings/tokens
+2. Copy your cli READ token
+3. Export `HF_TOKEN=<your cli READ token>`
+
+or with Docker:
+
+```shell
+model=meta-llama/Meta-Llama-3.1-8B-Instruct
+volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
+token=<your cli READ token>
+
+docker run --gpus all --shm-size 1g -e HF_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.4.0 --model-id $model
+```
+
+### A note on Shared Memory (shm)
+
+[`NCCL`](https://docs.nvidia.com/deeplearning/nccl/user-guide/docs/index.html) is a communication framework used by
+`PyTorch` to do distributed training/inference. `text-generation-inference` make
+use of `NCCL` to enable Tensor Parallelism to dramatically speed up inference for large language models.
+
+In order to share data between the different devices of a `NCCL` group, `NCCL` might fall back to using the host memory if
+peer-to-peer using NVLink or PCI is not possible.
+
+To allow the container to use 1G of Shared Memory and support SHM sharing, we add `--shm-size 1g` on the above command.
+
+If you are running `text-generation-inference` inside `Kubernetes`. You can also add Shared Memory to the container by
+creating a volume with:
+
+```yaml
+- name: shm
+  emptyDir:
+   medium: Memory
+   sizeLimit: 1Gi
+```
+
+and mounting it to `/dev/shm`.
+
+Finally, you can also disable SHM sharing by using the `NCCL_SHM_DISABLE=1` environment variable. However, note that
+this will impact performance.
+
+### Distributed Tracing
+
+`text-generation-inference` is instrumented with distributed tracing using OpenTelemetry. You can use this feature
+by setting the address to an OTLP collector with the `--otlp-endpoint` argument. The default service name can be
+overridden with the `--otlp-service-name` argument
+
+### Architecture
+
+![TGI architecture](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/TGI.png)
+
+Detailed blogpost by Adyen on TGI inner workings: [LLM inference at scale with TGI (Martin Iglesias Goyanes - Adyen, 2024)](https://www.adyen.com/knowledge-hub/llm-inference-at-scale-with-tgi)
+
+### Local install
+
+You can also opt to install `text-generation-inference` locally.
+
+First [install Rust](https://rustup.rs/) and create a Python virtual environment with at least
+Python 3.9, e.g. using `conda`:
 
-1. 安装Rust
 ```shell
 curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
+
+conda create -n text-generation-inference python=3.11
+conda activate text-generation-inference
 ```
 
-2. 安装Protoc
+You may also need to install Protoc.
+
+On Linux:
+
 ```shell
 PROTOC_ZIP=protoc-21.12-linux-x86_64.zip
 curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v21.12/$PROTOC_ZIP
@@ -49,50 +216,77 @@ sudo unzip -o $PROTOC_ZIP -d /usr/local bin/protoc
 sudo unzip -o $PROTOC_ZIP -d /usr/local 'include/*'
 rm -f $PROTOC_ZIP
 ```
-3. 安装TGI Service
-```bash
-git clone http://developer.hpccube.com/codes/wangkx1/text_generation_server-dcu.git # 根据需要的分支进行切换
 
-cd text-generation-inference
-pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
-pip install -r pre_requirements.txt
+On MacOS, using Homebrew:
 
-#安装exllama
-cd server
-make install-exllama #安装exllama kernels
-make install-exllamav2 #安装exllmav2 kernels
+```shell
+brew install protobuf
+```
 
-cd .. #回到项目根目录
-source $HOME/.cargo/env
-BUILD_EXTENSIONS=True make install #安装text-generation服务
+Then run:
 
+```shell
+BUILD_EXTENSIONS=True make install # Install repository and HF/transformer fork with CUDA kernels
+text-generation-launcher --model-id mistralai/Mistral-7B-Instruct-v0.2
 ```
-4. 安装benchmark
-```bash
-cd text-generation-inference
-make install-benchmark
-```
-注意：若安装过程过慢，可以通过如下命令修改默认源提速。
-```bash
 
+**Note:** on some machines, you may also need the OpenSSL libraries and gcc. On Linux machines, run:
+
+```shell
+sudo apt-get install libssl-dev gcc -y
 ```
-另外，`cargo install` 太慢也可以通过在`~/.cargo/config`中添加源来提速。
 
-## 查看安装的版本号
-```bash
-text-generation-launcher -V  #版本号与官方版本同步
+## Optimized architectures
+
+TGI works out of the box to serve optimized models for all modern models. They can be found in [this list](https://huggingface.co/docs/text-generation-inference/supported_models).
+
+Other architectures are supported on a best-effort basis using:
+
+`AutoModelForCausalLM.from_pretrained(<model>, device_map="auto")`
+
+or
+
+`AutoModelForSeq2SeqLM.from_pretrained(<model>, device_map="auto")`
+
+
+
+## Run locally
+
+### Run
+
+```shell
+text-generation-launcher --model-id mistralai/Mistral-7B-Instruct-v0.2
 ```
 
-## 使用前
+### Quantization
 
-```bash
-export PYTORCH_TUNABLEOP_ENABLED=0
+You can also run pre-quantized weights (AWQ, GPTQ, Marlin) or on-the-fly quantize weights with bitsandbytes, EETQ, fp8, to reduce the VRAM requirement:
+
+```shell
+text-generation-launcher --model-id mistralai/Mistral-7B-Instruct-v0.2 --quantize
 ```
 
-## Known Issue
+4bit quantization is available using the [NF4 and FP4 data types from bitsandbytes](https://arxiv.org/pdf/2305.14314.pdf). It can be enabled by providing `--quantize bitsandbytes-nf4` or `--quantize bitsandbytes-fp4` as a command line argument to `text-generation-launcher`.
+
+Read more about quantization in the [Quantization documentation](https://huggingface.co/docs/text-generation-inference/en/conceptual/quantization).
+
+## Develop
 
-- 无
+```shell
+make server-dev
+make router-dev
+```
+
+## Testing
 
-## 参考资料
-- [README_ORIGIN](README_ORIGIN.md)
-- [https://github.com/huggingface/text-generation-inference](https://github.com/huggingface/text-generation-inference)
+```shell
+# python
+make python-server-tests
+make python-client-tests
+# or both server and client tests
+make python-tests
+# rust cargo tests
+make rust-tests
+# integration tests
+make integration-tests
+```

README_ORINGIN.md

-<div align="center">
-
-<a href="https://www.youtube.com/watch?v=jlMAX2Oaht0">
-  <img width=560 width=315 alt="Making TGI deployment optimal" src="https://huggingface.co/datasets/Narsil/tgi_assets/resolve/main/thumbnail.png">
-</a>
-
-# Text Generation Inference
-
-<a href="https://github.com/huggingface/text-generation-inference">
-  <img alt="GitHub Repo stars" src="https://img.shields.io/github/stars/huggingface/text-generation-inference?style=social">
-</a>
-<a href="https://huggingface.github.io/text-generation-inference">
-  <img alt="Swagger API documentation" src="https://img.shields.io/badge/API-Swagger-informational">
-</a>
-
-A Rust, Python and gRPC server for text generation inference. Used in production at [HuggingFace](https://huggingface.co)
-to power Hugging Chat, the Inference API and Inference Endpoint.
-
-</div>
-
-## Table of contents
-
-- [Get Started](#get-started)
-  - [API Documentation](#api-documentation)
-  - [Using a private or gated model](#using-a-private-or-gated-model)
-  - [A note on Shared Memory](#a-note-on-shared-memory-shm)
-  - [Distributed Tracing](#distributed-tracing)
-  - [Local Install](#local-install)
-  - [CUDA Kernels](#cuda-kernels)
-- [Optimized architectures](#optimized-architectures)
-- [Run Mistral](#run-a-model)
-  - [Run](#run)
-  - [Quantization](#quantization)
-- [Develop](#develop)
-- [Testing](#testing)
-
-Text Generation Inference (TGI) is a toolkit for deploying and serving Large Language Models (LLMs). TGI enables high-performance text generation for the most popular open-source LLMs, including Llama, Falcon, StarCoder, BLOOM, GPT-NeoX, and [more](https://huggingface.co/docs/text-generation-inference/supported_models). TGI implements many features, such as:
-
-- Simple launcher to serve most popular LLMs
-- Production ready (distributed tracing with Open Telemetry, Prometheus metrics)
-- Tensor Parallelism for faster inference on multiple GPUs
-- Token streaming using Server-Sent Events (SSE)
-- Continuous batching of incoming requests for increased total throughput
-- Optimized transformers code for inference using [Flash Attention](https://github.com/HazyResearch/flash-attention) and [Paged Attention](https://github.com/vllm-project/vllm) on the most popular architectures
-- Quantization with :
-  - [bitsandbytes](https://github.com/TimDettmers/bitsandbytes)
-  - [GPT-Q](https://arxiv.org/abs/2210.17323)
-  - [EETQ](https://github.com/NetEase-FuXi/EETQ)
-  - [AWQ](https://github.com/casper-hansen/AutoAWQ)
-- [Safetensors](https://github.com/huggingface/safetensors) weight loading
-- Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226)
-- Logits warper (temperature scaling, top-p, top-k, repetition penalty, more details see [transformers.LogitsProcessor](https://huggingface.co/docs/transformers/internal/generation_utils#transformers.LogitsProcessor))
-- Stop sequences
-- Log probabilities
-- [Speculation](https://huggingface.co/docs/text-generation-inference/conceptual/speculation) ~2x latency
-- [Guidance/JSON](https://huggingface.co/docs/text-generation-inference/conceptual/guidance). Specify output format to speed up inference and make sure the output is valid according to some specs..
-- Custom Prompt Generation: Easily generate text by providing custom prompts to guide the model's output
-- Fine-tuning Support: Utilize fine-tuned models for specific tasks to achieve higher accuracy and performance
-
-### Hardware support
-
-- [Nvidia](https://github.com/huggingface/text-generation-inference/pkgs/container/text-generation-inference)
-- [AMD](https://github.com/huggingface/text-generation-inference/pkgs/container/text-generation-inference) (-rocm)
-- [Inferentia](https://github.com/huggingface/optimum-neuron/tree/main/text-generation-inference)
-- [Intel GPU](https://github.com/huggingface/text-generation-inference/pull/1475)
-- [Gaudi](https://github.com/huggingface/tgi-gaudi)
-- [Google TPU](https://huggingface.co/docs/optimum-tpu/howto/serving)
-
-
-## Get Started
-
-### Docker
-
-For a detailed starting guide, please see the [Quick Tour](https://huggingface.co/docs/text-generation-inference/quicktour). The easiest way of getting started is using the official Docker container:
-
-```shell
-model=HuggingFaceH4/zephyr-7b-beta
-volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
-
-docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.0 --model-id $model
-```
-
-And then you can make requests like
-
-```bash
-curl 127.0.0.1:8080/generate_stream \
-    -X POST \
-    -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":20}}' \
-    -H 'Content-Type: application/json'
-```
-
-**Note:** To use NVIDIA GPUs, you need to install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html). We also recommend using NVIDIA drivers with CUDA version 12.2 or higher. For running the Docker container on a machine with no GPUs or CUDA support, it is enough to remove the `--gpus all` flag and add `--disable-custom-kernels`, please note CPU is not the intended platform for this project, so performance might be subpar.
-
-**Note:** TGI supports AMD Instinct MI210 and MI250 GPUs. Details can be found in the [Supported Hardware documentation](https://huggingface.co/docs/text-generation-inference/supported_models#supported-hardware). To use AMD GPUs, please use `docker run --device /dev/kfd --device /dev/dri --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.0-rocm --model-id $model` instead of the command above.
-
-To see all options to serve your models (in the [code](https://github.com/huggingface/text-generation-inference/blob/main/launcher/src/main.rs) or in the cli):
-```
-text-generation-launcher --help
-```
-
-### API documentation
-
-You can consult the OpenAPI documentation of the `text-generation-inference` REST API using the `/docs` route.
-The Swagger UI is also available at: [https://huggingface.github.io/text-generation-inference](https://huggingface.github.io/text-generation-inference).
-
-### Using a private or gated model
-
-You have the option to utilize the `HUGGING_FACE_HUB_TOKEN` environment variable for configuring the token employed by
-`text-generation-inference`. This allows you to gain access to protected resources.
-
-For example, if you want to serve the gated Llama V2 model variants:
-
-1. Go to https://huggingface.co/settings/tokens
-2. Copy your cli READ token
-3. Export `HUGGING_FACE_HUB_TOKEN=<your cli READ token>`
-
-or with Docker:
-
-```shell
-model=meta-llama/Llama-2-7b-chat-hf
-volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
-token=<your cli READ token>
-
-docker run --gpus all --shm-size 1g -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.0 --model-id $model
-```
-
-### A note on Shared Memory (shm)
-
-[`NCCL`](https://docs.nvidia.com/deeplearning/nccl/user-guide/docs/index.html) is a communication framework used by
-`PyTorch` to do distributed training/inference. `text-generation-inference` make
-use of `NCCL` to enable Tensor Parallelism to dramatically speed up inference for large language models.
-
-In order to share data between the different devices of a `NCCL` group, `NCCL` might fall back to using the host memory if
-peer-to-peer using NVLink or PCI is not possible.
-
-To allow the container to use 1G of Shared Memory and support SHM sharing, we add `--shm-size 1g` on the above command.
-
-If you are running `text-generation-inference` inside `Kubernetes`. You can also add Shared Memory to the container by
-creating a volume with:
-
-```yaml
-- name: shm
-  emptyDir:
-   medium: Memory
-   sizeLimit: 1Gi
-```
-
-and mounting it to `/dev/shm`.
-
-Finally, you can also disable SHM sharing by using the `NCCL_SHM_DISABLE=1` environment variable. However, note that
-this will impact performance.
-
-### Distributed Tracing
-
-`text-generation-inference` is instrumented with distributed tracing using OpenTelemetry. You can use this feature
-by setting the address to an OTLP collector with the `--otlp-endpoint` argument.
-
-### Architecture
-
-![TGI architecture](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/TGI.png)
-
-### Local install
-
-You can also opt to install `text-generation-inference` locally.
-
-First [install Rust](https://rustup.rs/) and create a Python virtual environment with at least
-Python 3.9, e.g. using `conda`:
-
-```shell
-curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
-
-conda create -n text-generation-inference python=3.11
-conda activate text-generation-inference
-```
-
-You may also need to install Protoc.
-
-On Linux:
-
-```shell
-PROTOC_ZIP=protoc-21.12-linux-x86_64.zip
-curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v21.12/$PROTOC_ZIP
-sudo unzip -o $PROTOC_ZIP -d /usr/local bin/protoc
-sudo unzip -o $PROTOC_ZIP -d /usr/local 'include/*'
-rm -f $PROTOC_ZIP
-```
-
-On MacOS, using Homebrew:
-
-```shell
-brew install protobuf
-```
-
-Then run:
-
-```shell
-BUILD_EXTENSIONS=True make install # Install repository and HF/transformer fork with CUDA kernels
-text-generation-launcher --model-id mistralai/Mistral-7B-Instruct-v0.2
-```
-
-**Note:** on some machines, you may also need the OpenSSL libraries and gcc. On Linux machines, run:
-
-```shell
-sudo apt-get install libssl-dev gcc -y
-```
-
-## Optimized architectures
-
-TGI works out of the box to serve optimized models for all modern models. They can be found in [this list](https://huggingface.co/docs/text-generation-inference/supported_models).
-
-Other architectures are supported on a best-effort basis using:
-
-`AutoModelForCausalLM.from_pretrained(<model>, device_map="auto")`
-
-or
-
-`AutoModelForSeq2SeqLM.from_pretrained(<model>, device_map="auto")`
-
-
-
-## Run locally
-
-### Run
-
-```shell
-text-generation-launcher --model-id mistralai/Mistral-7B-Instruct-v0.2
-```
-
-### Quantization
-
-You can also quantize the weights with bitsandbytes to reduce the VRAM requirement:
-
-```shell
-text-generation-launcher --model-id mistralai/Mistral-7B-Instruct-v0.2 --quantize
-```
-
-4bit quantization is available using the [NF4 and FP4 data types from bitsandbytes](https://arxiv.org/pdf/2305.14314.pdf). It can be enabled by providing `--quantize bitsandbytes-nf4` or `--quantize bitsandbytes-fp4` as a command line argument to `text-generation-launcher`.
-
-## Develop
-
-```shell
-make server-dev
-make router-dev
-```
-
-## Testing
-
-```shell
-# python
-make python-server-tests
-make python-client-tests
-# or both server and client tests
-make python-tests
-# rust cargo tests
-make rust-tests
-# integration tests
-make integration-tests
-```

router/client/src/v3/client.rs → backends/client/src/v3/client.rs

@@ -153,9 +153,13 @@ impl Client {
                 }),
                 // We truncate the input on the server side to be sure that it has the correct size
                 truncate,
+                // Most request will have that
+                add_special_tokens: true,
                 // Blocks and slots will be set on the server side if we use paged attention
                 blocks: vec![],
                 slots: vec![],
+                cache_len: 0,
+                chunk_len: None,
                 // Set sampling parameters to also take these ops into account in the max memory
                 parameters: Some(NextTokenChooserParameters {
                     temperature: 0.9,
@@ -214,8 +218,13 @@ impl Client {
     pub async fn prefill(
         &mut self,
         batch: Batch,
+        cached_batch: Option<CachedBatch>,
     ) -> Result<(Vec<Generation>, Option<CachedBatch>, PrefillTimings)> {
-        let request = tonic::Request::new(PrefillRequest { batch: Some(batch) }).inject_context();
+        let request = tonic::Request::new(PrefillRequest {
+            batch: Some(batch),
+            cached_batch,
+        })
+        .inject_context();
         let response = self.stub.prefill(request).await?.into_inner();
         Ok((
             response.generations,

router/client/src/v3/sharded_client.rs → backends/client/src/v3/sharded_client.rs

@@ -134,11 +134,12 @@ impl ShardedClient {
     pub async fn prefill(
         &mut self,
         batch: Batch,
+        cached_batch: Option<CachedBatch>,
     ) -> Result<(Vec<Generation>, Option<CachedBatch>, PrefillTimings)> {
         let futures: Vec<_> = self
             .clients
             .iter_mut()
-            .map(|client| Box::pin(client.prefill(batch.clone())))
+            .map(|client| Box::pin(client.prefill(batch.clone(), cached_batch.clone())))
             .collect();
         #[allow(clippy::type_complexity)]
         let results: Result<Vec<(Vec<Generation>, Option<CachedBatch>, PrefillTimings)>> =
@@ -221,6 +222,7 @@ impl Health for ShardedClient {
                 chunks: vec![Chunk::Text("liveness".into()).into()],
             }),
             truncate: 10,
+            add_special_tokens: true,
             prefill_logprobs: false,
             parameters: Some(NextTokenChooserParameters {
                 temperature: 1.0,
@@ -244,6 +246,8 @@ impl Health for ShardedClient {
             // Block 0 is reserved for health checks
             blocks: vec![0],
             slots: (0..16).collect(),
+            cache_len: 0,
+            chunk_len: None,
             adapter_id: None,
         };
         let batch = Batch {
@@ -253,7 +257,7 @@ impl Health for ShardedClient {
             max_tokens: 2,
             max_blocks: 1,
         };
-        self.clone().prefill(batch).await?;
+        self.clone().prefill(batch, None).await?;
         Ok(())
     }
 }