v2.0.1

Cargo.lock

@@ -3393,7 +3393,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-benchmark"
-version = "2.0.0"
+version = "2.0.1"
 dependencies = [
  "average",
  "clap",
@@ -3414,7 +3414,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-client"
-version = "2.0.0"
+version = "2.0.1"
 dependencies = [
  "futures",
  "grpc-metadata",
@@ -3430,7 +3430,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-launcher"
-version = "2.0.0"
+version = "2.0.1"
 dependencies = [
  "clap",
  "ctrlc",
@@ -3448,7 +3448,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-router"
-version = "2.0.0"
+version = "2.0.1"
 dependencies = [
  "async-stream",
  "axum",

Cargo.toml

@@ -9,7 +9,7 @@ members = [
 resolver = "2"
 
 [workspace.package]
-version = "2.0.0"
+version = "2.0.1"
 edition = "2021"
 authors = ["Olivier Dehaene"]
 homepage = "https://github.com/huggingface/text-generation-inference"

docs/openapi.json

@@ -10,7 +10,7 @@
       "name": "Apache 2.0",
       "url": "https://www.apache.org/licenses/LICENSE-2.0"
     },
-    "version": "2.0.0"
+    "version": "2.0.1"
   },
   "paths": {
     "/": {

integration-tests/models/__snapshots__/test_chat_llama/test_flash_llama_simple.json

@@ -17,7 +17,7 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "2.0.0-native",
+  "system_fingerprint": "2.0.1-native",
   "usage": {
     "completion_tokens": 100,
     "prompt_tokens": 60,

integration-tests/models/__snapshots__/test_completion_prompts/test_flash_llama_completion_many_prompts.json

@@ -29,7 +29,7 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "2.0.0-native",
+  "system_fingerprint": "2.0.1-native",
   "usage": {
     "completion_tokens": 36,
     "prompt_tokens": 8,

integration-tests/models/__snapshots__/test_completion_prompts/test_flash_llama_completion_many_prompts_stream.json

@@ -12,7 +12,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -27,7 +27,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -42,7 +42,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -57,7 +57,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -72,7 +72,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -87,7 +87,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -102,7 +102,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -117,7 +117,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -132,7 +132,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -147,7 +147,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -162,7 +162,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -177,7 +177,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -192,7 +192,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -207,7 +207,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -222,7 +222,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -237,7 +237,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -252,7 +252,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -267,7 +267,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -282,7 +282,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -297,7 +297,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -312,7 +312,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -327,7 +327,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -342,7 +342,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -357,7 +357,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -372,7 +372,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -387,7 +387,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -402,7 +402,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -417,7 +417,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -432,7 +432,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -447,7 +447,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -462,7 +462,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -477,7 +477,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -492,7 +492,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -507,7 +507,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -522,7 +522,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -537,7 +537,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -552,7 +552,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -567,7 +567,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -582,7 +582,7 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   },
   {
     "choices": [
@@ -597,6 +597,6 @@
     "id": "",
     "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     "object": "text_completion",
-    "system_fingerprint": "2.0.0-native"
+    "system_fingerprint": "2.0.1-native"
   }
 ]

integration-tests/models/__snapshots__/test_completion_prompts/test_flash_llama_completion_single_prompt.json

@@ -11,7 +11,7 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "2.0.0-native",
+  "system_fingerprint": "2.0.1-native",
   "usage": {
     "completion_tokens": 5,
     "prompt_tokens": 6,

integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools.json

@@ -30,7 +30,7 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "2.0.0-native",
+  "system_fingerprint": "2.0.1-native",
   "usage": {
     "completion_tokens": 37,
     "prompt_tokens": 524,

integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_auto.json

@@ -30,7 +30,7 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "2.0.0-native",
+  "system_fingerprint": "2.0.1-native",
   "usage": {
     "completion_tokens": 37,
     "prompt_tokens": 524,

integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_choice.json

@@ -30,7 +30,7 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "2.0.0-native",
+  "system_fingerprint": "2.0.1-native",
   "usage": {
     "completion_tokens": 48,
     "prompt_tokens": 320,

integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_stream.json

@@ -23,5 +23,5 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "2.0.0-native"
+  "system_fingerprint": "2.0.1-native"
 }

integration-tests/pyproject.toml

 [tool.poetry]
 name = "text-generation-integration-tests"
-version = "2.0.0"
+version = "2.0.1"
 description = "Text Generation Inference integration tests"
 authors = ["Nicolas Patry <nicolas@huggingface.co>"]
 

server/pyproject.toml

 [tool.poetry]
 name = "text-generation-server"
-version = "2.0.0"
+version = "2.0.1"
 description = "Text Generation Inference Python gRPC Server"
 authors = ["Olivier Dehaene <olivier@huggingface.co>"]