diff --git a/Cargo.lock b/Cargo.lock
index 5c01aeeb..68d96726 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -2960,7 +2960,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-benchmark"
-version = "1.4.3"
+version = "1.4.4"
 dependencies = [
  "average",
  "clap",
@@ -2981,7 +2981,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-client"
-version = "1.4.3"
+version = "1.4.4"
 dependencies = [
  "futures",
  "grpc-metadata",
@@ -2998,7 +2998,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-launcher"
-version = "1.4.3"
+version = "1.4.4"
 dependencies = [
  "clap",
  "ctrlc",
@@ -3014,7 +3014,7 @@ dependencies = [
 
 [[package]]
 name = "text-generation-router"
-version = "1.4.3"
+version = "1.4.4"
 dependencies = [
  "async-stream",
  "axum",
diff --git a/Cargo.toml b/Cargo.toml
index 820eb0aa..d76cbc68 100644
--- a/Cargo.toml
+++ b/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"
diff --git a/docs/openapi.json b/docs/openapi.json
index e5ffba5e..75965d98 100644
--- a/docs/openapi.json
+++ b/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": {
     "/": {
diff --git a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_no_tools.json b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_no_tools.json
index 463c6ce0..467b8ce3 100644
--- a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_no_tools.json
+++ b/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,
diff --git a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools.json b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools.json
index 7cdc4265..8bdb7465 100644
--- a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools.json
+++ b/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,
diff --git a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_auto.json b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_auto.json
index dc59e919..5ba297b1 100644
--- a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_auto.json
+++ b/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,
diff --git a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_choice.json b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_choice.json
index e5e8e690..522624bc 100644
--- a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_choice.json
+++ b/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,
diff --git a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_stream.json b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_stream.json
index 6eb5fe0d..c085100d 100644
--- a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_stream.json
+++ b/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"
 }
diff --git a/integration-tests/pyproject.toml b/integration-tests/pyproject.toml
index f3599b29..cab74c46 100644
--- a/integration-tests/pyproject.toml
+++ b/integration-tests/pyproject.toml
@@ -1,6 +1,6 @@
 [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>"]
 
diff --git a/server/pyproject.toml b/server/pyproject.toml
index 2e8c2945..2fdfa8b8 100644
--- a/server/pyproject.toml
+++ b/server/pyproject.toml
@@ -1,6 +1,6 @@
 [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>"]