chore: upgrade modelexpress version (#8336)

Signed-off-by: Nate Mailhot <nmailhot@nvidia.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>

Cargo.lock

@@ -1464,7 +1464,7 @@ version = "3.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "faf9468729b8cbcea668e36183cb69d317348c2e08e994829fb56ebfdfbaac34"
 dependencies = [
- "windows-sys 0.48.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -2263,7 +2263,7 @@ dependencies = [
  "libc",
  "option-ext",
  "redox_users",
- "windows-sys 0.59.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -2808,7 +2808,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
 dependencies = [
  "libc",
- "windows-sys 0.59.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -4095,7 +4095,7 @@ checksum = "3640c1c38b8e4e43584d8df18be5fc6b0aa314ce6ebf51b53313d4306cca8e46"
 dependencies = [
  "hermit-abi 0.5.2",
  "libc",
- "windows-sys 0.59.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -4167,7 +4167,7 @@ dependencies = [
  "portable-atomic",
  "portable-atomic-util",
  "serde_core",
- "windows-sys 0.59.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -5049,9 +5049,9 @@ dependencies = [
 
 [[package]]
 name = "modelexpress-client"
-version = "0.2.2"
+version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a9929c605e135347ccda5e0e7ff0627217f23189915a5c3971265ce490a14abf"
+checksum = "7de62490b58d9862482a2cf223c3aeceaadd01d46ac996d99b4b6a75af204d21"
 dependencies = [
  "anyhow",
  "clap 4.6.0",
@@ -5071,9 +5071,9 @@ dependencies = [
 
 [[package]]
 name = "modelexpress-common"
-version = "0.2.2"
+version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4997c93ac4b3ded7a999eff0b770aea2448d808ce7f020729e6af11e4c08fe67"
+checksum = "44ec153f868d45d5d48129dd2f1e24755e93f74d6f9f423094a3b784fa6a88cc"
 dependencies = [
  "anyhow",
  "async-trait",
@@ -5344,7 +5344,7 @@ version = "0.50.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7957b9740744892f114936ab4a57b3f487491bbeafaf8083688b16841a4240e5"
 dependencies = [
- "windows-sys 0.59.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -6436,7 +6436,7 @@ version = "0.13.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "be769465445e8c1474e9c5dac2018218498557af32d9ed057325ec9a41ae81bf"
 dependencies = [
- "heck 0.4.1",
+ "heck 0.5.0",
  "itertools 0.14.0",
  "log",
  "multimap",
@@ -6456,7 +6456,7 @@ version = "0.14.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "343d3bd7056eda839b03204e68deff7d1b13aba7af2b2fd16890697274262ee7"
 dependencies = [
- "heck 0.4.1",
+ "heck 0.5.0",
  "itertools 0.14.0",
  "log",
  "multimap",
@@ -6657,7 +6657,7 @@ dependencies = [
  "once_cell",
  "socket2 0.6.3",
  "tracing",
- "windows-sys 0.59.0",
+ "windows-sys 0.60.2",
 ]
 
 [[package]]
@@ -7300,7 +7300,7 @@ dependencies = [
  "errno",
  "libc",
  "linux-raw-sys 0.12.1",
- "windows-sys 0.59.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -8262,7 +8262,7 @@ dependencies = [
  "getrandom 0.4.2",
  "once_cell",
  "rustix 1.1.4",
- "windows-sys 0.59.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -9854,7 +9854,7 @@ version = "0.1.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
 dependencies = [
- "windows-sys 0.48.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]

Cargo.toml

@@ -88,8 +88,8 @@ hf-hub = { version = "0.4.2", default-features = false, features = [
 ] }
 
 # ModelExpress for model downloading
-modelexpress-client = { version = "0.2.0" }
-modelexpress-common = { version = "0.2.0" }
+modelexpress-client = { version = "0.3.0" }
+modelexpress-common = { version = "0.3.0" }
 
 humantime = { version = "2.2.0" }
 indexmap = { version = "2" }

container/context.yaml

@@ -72,7 +72,7 @@ vllm:
   enable_gpu_memory_service: "true"
   enable_kvbm: "true"
   enable_modelexpress_p2p: "false"
-  modelexpress_ref: "3d73992ce6c10e52ddc54f7f12af35d27e173f15"
+  modelexpress_ref: "76fc5d7f06c37121ee8789a29fac6f9b08c4743a"  # v0.3.0
 
 sglang:
   cuda12.9:

lib/bindings/kvbm/Cargo.lock

@@ -3631,9 +3631,9 @@ dependencies = [
 
 [[package]]
 name = "modelexpress-client"
-version = "0.2.2"
+version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a9929c605e135347ccda5e0e7ff0627217f23189915a5c3971265ce490a14abf"
+checksum = "7de62490b58d9862482a2cf223c3aeceaadd01d46ac996d99b4b6a75af204d21"
 dependencies = [
  "anyhow",
  "clap",
@@ -3653,9 +3653,9 @@ dependencies = [
 
 [[package]]
 name = "modelexpress-common"
-version = "0.2.2"
+version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4997c93ac4b3ded7a999eff0b770aea2448d808ce7f020729e6af11e4c08fe67"
+checksum = "44ec153f868d45d5d48129dd2f1e24755e93f74d6f9f423094a3b784fa6a88cc"
 dependencies = [
  "anyhow",
  "async-trait",

lib/bindings/python/Cargo.lock

@@ -3691,9 +3691,9 @@ dependencies = [
 
 [[package]]
 name = "modelexpress-client"
-version = "0.2.2"
+version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a9929c605e135347ccda5e0e7ff0627217f23189915a5c3971265ce490a14abf"
+checksum = "7de62490b58d9862482a2cf223c3aeceaadd01d46ac996d99b4b6a75af204d21"
 dependencies = [
  "anyhow",
  "clap",
@@ -3713,9 +3713,9 @@ dependencies = [
 
 [[package]]
 name = "modelexpress-common"
-version = "0.2.2"
+version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4997c93ac4b3ded7a999eff0b770aea2448d808ce7f020729e6af11e4c08fe67"
+checksum = "44ec153f868d45d5d48129dd2f1e24755e93f74d6f9f423094a3b784fa6a88cc"
 dependencies = [
  "anyhow",
  "async-trait",

lib/llm/src/hub.rs

@@ -112,7 +112,10 @@ pub async fn from_hf(name: impl AsRef<Path>, ignore_weights: bool) -> anyhow::Re
             {
                 Ok(()) => {
                     tracing::info!("Server download succeeded for model: {model_name}");
-                    match client.get_model_path(&model_name).await {
+                    match client
+                        .get_model_path(&model_name, MxModelProvider::HuggingFace)
+                        .await
+                    {
                         Ok(path) => Ok(path),
                         Err(e) => {
                             tracing::warn!(