[CPU] toml file update (#17861)

docker/xeon.Dockerfile

@@ -4,12 +4,6 @@ SHELL ["/bin/bash", "-c"]
 ARG SGLANG_REPO=https://github.com/sgl-project/sglang.git
 ARG VER_SGLANG=main
 
-ARG VER_TORCH=2.9.0
-ARG VER_TORCHVISION=0.24.0
-ARG VER_TORCHAUDIO=2.9.0
-ARG VER_TORCHAO=0.14.1
-ARG VER_TRITON=3.5.0
-
 RUN apt-get update && \
     apt-get full-upgrade -y && \
     DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y \
@@ -46,8 +40,6 @@ RUN source $HOME/.local/bin/env && \
     cd python && \
     cp pyproject_cpu.toml pyproject.toml && \
     uv pip install . && \
-    uv pip install torch==${VER_TORCH} torchvision==${VER_TORCHVISION} torchaudio==${VER_TORCHAUDIO} torchao==${VER_TORCHAO} triton==${VER_TRITON} --force-reinstall && \
-    uv pip install tabulate && \
     cd ../sgl-kernel && \
     cp pyproject_cpu.toml pyproject.toml && \
     uv pip install .

docs/platforms/cpu_server.md

@@ -123,7 +123,6 @@ cp pyproject_cpu.toml pyproject.toml
 # Install SGLang dependent libs, and build SGLang main package
 uv pip install --upgrade pip setuptools
 uv pip install .
-uv pip install torch==2.9.0 torchvision==0.24.0 torchaudio==2.9.0 torchao==0.14.1 triton==3.5.0 --force-reinstall
 
 # Build the CPU backend kernels
 cd ../sgl-kernel
@@ -187,8 +186,7 @@ Notes:
 2. The flag `--tp 6` specifies that tensor parallelism will be applied using 6 ranks (TP6).
     The number of TP specified is how many TP ranks will be used during the execution.
     On a CPU platform, a TP rank means a sub-NUMA cluster (SNC).
-    Usually we can get the SNC information (How many available) from the Operating System.
-    Users can specify TP to be no more than the total available SNCs in current system.
+    Usually we can get the SNC information (How many available) from the Operating System with e.g. `lscpu` command.
 
     If the specified TP rank number differs from the total SNC count,
     the system will automatically utilize the first `n` SNCs.

python/pyproject_cpu.toml

@@ -39,7 +39,7 @@ dependencies = [
   "openai-harmony==0.0.4",
   "openai==2.6.1",
   "orjson",
-  "outlines==0.1.11",
+  "outlines",
   "packaging",
   "partial_json_parser",
   "pillow",
@@ -55,11 +55,16 @@ dependencies = [
   "sentencepiece",
   "setproctitle",
   "soundfile==0.13.1",
+  "tabulate",
   "tiktoken",
   "timm==1.0.16",
-  "torchao==0.9.0",
+  "torch==2.9.0",
+  "torchao==0.14.1",
+  "torchaudio==2.9.0",
+  "torchvision==0.24.0",
   "tqdm",
   "transformers==4.57.1",
+  "triton==3.5.0",
   "uvicorn",
   "uvloop",
   "xgrammar==0.1.27",
@@ -84,7 +89,6 @@ test = [
   "peft",
   "pytest",
   "sentence_transformers",
-  "tabulate",
 ]
 all = []
 dev = ["sglang[test]"]

sgl-kernel/pyproject_cpu.toml

@@ -7,7 +7,7 @@ requires = [
 build-backend = "scikit_build_core.build"
 
 [project]
-name = "sgl-kernel-cpu"
+name = "sglang-kernel-cpu"
 version = "0.3.21"
 description = "Kernel Library for SGLang"
 readme = "README.md"