feat: sglang update to 0.5.7 (#5148)

benchmarks/pyproject.toml

@@ -46,7 +46,7 @@ dependencies = [
     "pydantic>=2",
     "tabulate",
     "types-tabulate",
-    # Satisfies vLLM 0.11.0 (>=4.55.2), vLLM 0.11.2 (>=4.56.0,<5), TRT-LLM 1.2.0rc6 (==4.56.0), SGLang 0.5.6.post2 (==4.57.1)
+    # Satisfies vLLM 0.11.0 (>=4.55.2), vLLM 0.11.2 (>=4.56.0,<5), TRT-LLM 1.2.0rc6 (==4.56.0), SGLang 0.5.7 (==4.57.1)
     "transformers>=4.56.0,<=4.57.1",
     "pytest-mypy",
 ]

container/Dockerfile.sglang

@@ -41,7 +41,7 @@ ARG ENABLE_MEDIA_FFMPEG
 ARG CARGO_BUILD_JOBS
 
 ARG RUNTIME_IMAGE="lmsysorg/sglang"
-ARG RUNTIME_IMAGE_TAG="v0.5.6.post2-runtime"
+ARG RUNTIME_IMAGE_TAG="v0.5.7-runtime"
 
 # SCCACHE configuration
 ARG USE_SCCACHE

container/deps/requirements.txt

@@ -53,7 +53,7 @@ tensorboardX==2.6.2.2
 # Transformers version constraint for container builds
 # - vLLM 0.11.0: >=4.55.2, vLLM 0.11.2: >=4.56.0,<5
 # - TensorRT-LLM 1.2.0rc6: ==4.56.0
-# - SGLang 0.5.6.post2: ==4.57.1
+# - SGLang 0.5.7: ==4.57.1
 # Using >=4.56.0 and <=4.57.1 to satisfy all frameworks
 transformers>=4.56.0,<=4.57.1
 types-aiofiles==25.1.0.20251011

docs/reference/support-matrix.md

@@ -62,7 +62,7 @@ The following table shows the dependency versions included with each Dynamo rele
 
 | **Dependency** | **main (ToT)** | **v0.8.0 (unreleased)** | **v0.7.1** | **v0.7.0.post1** | **v0.7.0** |
 | :------------- | :------------- | :---------------------- | :--------- | :--------------- | :--------- |
-| SGLang         | 0.5.6.post2    | 0.5.6.post2             | 0.5.3.post4| 0.5.3.post4      | 0.5.3.post4|
+| SGLang         | 0.5.7          | 0.5.7                   | 0.5.3.post4| 0.5.3.post4      | 0.5.3.post4|
 | TensorRT-LLM   | 1.2.0rc6       | 1.2.0rc6                | 1.2.0rc3   | 1.2.0rc3         | 1.2.0rc2   |
 | vLLM           | 0.13.0         | 0.12.0                  | 0.11.0     | 0.11.0           | 0.11.0     |
 | NIXL           | 0.8.0          | 0.8.0                   | 0.8.0      | 0.8.0            | 0.8.0      |

pyproject.toml

@@ -61,7 +61,7 @@ vllm = [
 
 sglang = [
     "uvloop",
-    "sglang==0.5.6.post2",
+    "sglang==0.5.7",
     "nixl[cu12]<=0.8.0",
 ]