v1.4.4 (#1668)

Cargo.toml

@@ -9,7 +9,7 @@ members = [
 resolver = "2"
 
 [workspace.package]
-version = "1.4.3"
+version = "1.4.4"
 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": "1.4.3"
+    "version": "1.4.4"
   },
   "paths": {
     "/": {

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

@@ -17,7 +17,7 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "1.4.3-native",
+  "system_fingerprint": "1.4.4-native",
   "usage": {
     "completion_tokens": 100,
     "prompt_tokens": 60,

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

@@ -31,7 +31,7 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "1.4.3-native",
+  "system_fingerprint": "1.4.4-native",
   "usage": {
     "completion_tokens": 29,
     "prompt_tokens": 316,

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

@@ -31,7 +31,7 @@
   "id": "",
   "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "object": "text_completion",
-  "system_fingerprint": "1.4.3-native",
+  "system_fingerprint": "1.4.4-native",
   "usage": {
     "completion_tokens": 29,
     "prompt_tokens": 316,

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": "1.4.3-native",
+  "system_fingerprint": "1.4.4-native",
   "usage": {
     "completion_tokens": 21,
     "prompt_tokens": 187,

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": "1.4.3-native"
+  "system_fingerprint": "1.4.4-native"
 }

integration-tests/pyproject.toml

 [tool.poetry]
 name = "text-generation-integration-tests"
-version = "1.4.3"
+version = "1.4.4"
 description = "Text Generation Inference integration tests"
 authors = ["Nicolas Patry <nicolas@huggingface.co>"]
 

server/pyproject.toml

 [tool.poetry]
 name = "text-generation-server"
-version = "1.4.3"
+version = "1.4.4"
 description = "Text Generation Inference Python gRPC Server"
 authors = ["Olivier Dehaene <olivier@huggingface.co>"]