Dedicated toml files for CPU/XPU (#10734)

.github/workflows/pr-test-xeon.yml

@@ -42,7 +42,10 @@ jobs:
           version=$(cat python/sglang/version.py | cut -d'"' -f2)
           tag=v${version}-xeon
 
-          docker build . -f docker/Dockerfile.xeon  -t sglang_xeon --no-cache
+          docker build \
+            --build-arg SGLANG_REPO=${{ github.event.pull_request.head.repo.clone_url }} \
+            --build-arg VER_SGLANG=${{ github.head_ref }} \
+            . -f docker/Dockerfile.xeon  -t sglang_xeon --no-cache
 
       - name: Run container
         run: |

docker/Dockerfile.xeon

 FROM ubuntu:24.04
 SHELL ["/bin/bash", "-c"]
 
+ARG SGLANG_REPO=https://github.com/sgl-project/sglang.git
 ARG VER_SGLANG=main
+
 ARG VER_TORCH=2.7.1
 ARG VER_TORCHVISION=0.22.1
 ARG VER_TRITON=3.3.1
@@ -20,7 +22,7 @@ RUN apt-get update && \
 
 WORKDIR /sgl-workspace
 
-RUN curl -fsSL -v -o miniforge.sh -O https://github.com/conda-forge/miniforge/releases/download/24.11.3-2/Miniforge3-24.11.3-2-Linux-x86_64.sh && \
+RUN curl -fsSL -o miniforge.sh -O https://github.com/conda-forge/miniforge/releases/download/25.3.1-0/Miniforge3-25.3.1-0-Linux-x86_64.sh && \
     bash miniforge.sh -b -p ./miniforge3 && \
     rm -f miniforge.sh && \
     . miniforge3/bin/activate && \
@@ -33,13 +35,14 @@ ENV CONDA_PREFIX=/sgl-workspace/miniforge3
 RUN pip config set global.index-url https://download.pytorch.org/whl/cpu && \
     pip config set global.extra-index-url https://pypi.org/simple
 
-RUN git clone https://github.com/sgl-project/sglang.git && \
+RUN git clone ${SGLANG_REPO} && \
     cd sglang && \
-    rm -rf python/pyproject.toml && mv python/pyproject_other.toml python/pyproject.toml && \
     git checkout ${VER_SGLANG} && \
-    pip install -e "python[all_cpu]" && \
+    cd python && \
+    cp pyproject_cpu.toml pyproject.toml && \
+    pip install . && \
     pip install torch==${VER_TORCH} torchvision==${VER_TORCHVISION} triton==${VER_TRITON} --force-reinstall && \
-    cd sgl-kernel && \
+    cd ../sgl-kernel && \
     cp pyproject_cpu.toml pyproject.toml && \
     pip install .
 

docs/platforms/cpu_server.md

@@ -82,15 +82,16 @@ cd sglang
 git checkout <YOUR-DESIRED-VERSION>
 
 # Use dedicated toml file
-cp python/pyproject_other.toml python/pyproject.toml
+cd python
+cp pyproject_cpu.toml pyproject.toml
 # Install SGLang dependent libs, and build SGLang main package
 pip install --upgrade pip setuptools
 conda install -y libsqlite==3.48.0 gperftools tbb libnuma numactl
-pip install -e "python[all_cpu]"
+pip install .
 pip install torch==2.7.1 torchvision==0.22.1 triton==3.3.1 --force-reinstall
 
 # Build the CPU backend kernels
-cd sgl-kernel
+cd ../sgl-kernel
 cp pyproject_cpu.toml pyproject.toml
 pip install .
 

python/pyproject_cpu.toml

+# https://docs.sglang.ai/platforms/cpu_server.html
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "sglang"
+version = "0.5.3rc0"
+description = "SGLang is a fast serving framework for large language models and vision language models."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { file = "LICENSE" }
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: Apache Software License",
+]
+
+dependencies = [
+    "aiohttp",
+    "anthropic>=0.20.0",
+    "blobfile==3.0.0",
+    "build",
+    "compressed-tensors",
+    "datasets",
+    "decord",
+    "einops",
+    "fastapi",
+    "hf_transfer",
+    "huggingface_hub",
+    "intel-openmp",
+    "interegular",
+    "IPython",
+    "llguidance>=0.7.11,<0.8.0",
+    "modelscope",
+    "msgspec",
+    "ninja",
+    "numpy",
+    "openai==1.99.1",
+    "openai-harmony==0.0.4",
+    "orjson",
+    "outlines==0.1.11",
+    "packaging",
+    "partial_json_parser",
+    "pillow",
+    "prometheus-client>=0.20.0",
+    "psutil",
+    "pybase64",
+    "pydantic",
+    "python-multipart",
+    "pyzmq>=25.1.2",
+    "requests",
+    "scipy",
+    "sentencepiece",
+    "setproctitle",
+    "soundfile==0.13.1",
+    "tiktoken",
+    "timm==1.0.16",
+    "torchao==0.9.0",
+    "tqdm",
+    "transformers==4.56.1",
+    "uvicorn",
+    "uvloop",
+    "xgrammar==0.1.24",
+]
+
+[project.optional-dependencies]
+tracing = [
+    "opentelemetry-sdk",
+    "opentelemetry-api",
+    "opentelemetry-exporter-otlp",
+    "opentelemetry-exporter-otlp-proto-grpc",
+]
+
+test = [
+    "accelerate",
+    "expecttest",
+    "jsonlines",
+    "matplotlib",
+    "pandas",
+    "peft",
+    "sentence_transformers",
+    "pytest",
+    "tabulate",
+]
+
+dev = ["sglang", "sglang[test]"]
+
+[project.urls]
+"Homepage" = "https://github.com/sgl-project/sglang"
+"Bug Tracker" = "https://github.com/sgl-project/sglang/issues"
+
+[tool.setuptools.package-data]
+"sglang" = [
+    "srt/layers/moe/fused_moe_triton/configs/*/*.json",
+    "srt/layers/quantization/configs/*.json",
+    "srt/mem_cache/storage/hf3fs/hf3fs_utils.cpp",
+]
+
+[tool.setuptools.packages.find]
+exclude = [
+    "assets*",
+    "benchmark*",
+    "docs*",
+    "dist*",
+    "playground*",
+    "scripts*",
+    "tests*",
+]
+
+[tool.wheel]
+exclude = [
+    "assets*",
+    "benchmark*",
+    "docs*",
+    "dist*",
+    "playground*",
+    "scripts*",
+    "tests*",
+]
+
+[tool.codespell]
+ignore-words-list = "ans, als, hel, boostrap, childs, te, vas, hsa, ment"
+skip = "*.json,*.jsonl,*.patch,*.txt"

python/pyproject_xpu.toml

+# xpu is not enabled in public vllm and torch whl,
+# need to follow https://docs.vllm.ai/en/latest/getting_started/xpu-installation.html install vllm
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "sglang"
+version = "0.5.3rc0"
+description = "SGLang is a fast serving framework for large language models and vision language models."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { file = "LICENSE" }
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: Apache Software License",
+]
+
+dependencies = [
+    "aiohttp",
+    "anthropic>=0.20.0",
+    "blobfile==3.0.0",
+    "build",
+    "compressed-tensors",
+    "datasets",
+    "decord",
+    "einops",
+    "fastapi",
+    "hf_transfer",
+    "huggingface_hub",
+    "interegular",
+    "IPython",
+    "llguidance>=0.7.11,<0.8.0",
+    "modelscope",
+    "msgspec",
+    "ninja",
+    "numpy",
+    "openai==1.99.1",
+    "openai-harmony==0.0.4",
+    "orjson",
+    "outlines==0.1.11",
+    "packaging",
+    "partial_json_parser",
+    "pillow",
+    "prometheus-client>=0.20.0",
+    "psutil",
+    "pybase64",
+    "pydantic",
+    "python-multipart",
+    "pyzmq>=25.1.2",
+    "requests",
+    "scipy",
+    "sentencepiece",
+    "setproctitle",
+    "soundfile==0.13.1",
+    "tiktoken",
+    "timm==1.0.16",
+    "torchao==0.9.0",
+    "tqdm",
+    "transformers==4.56.1",
+    "uvicorn",
+    "uvloop",
+    "xgrammar==0.1.24",
+]
+
+[project.optional-dependencies]
+tracing = [
+    "opentelemetry-sdk",
+    "opentelemetry-api",
+    "opentelemetry-exporter-otlp",
+    "opentelemetry-exporter-otlp-proto-grpc",
+]
+
+test = [
+    "accelerate",
+    "expecttest",
+    "jsonlines",
+    "matplotlib",
+    "pandas",
+    "peft",
+    "sentence_transformers",
+    "pytest",
+    "tabulate",
+]
+
+dev = ["sglang", "sglang[test]"]
+
+[project.urls]
+"Homepage" = "https://github.com/sgl-project/sglang"
+"Bug Tracker" = "https://github.com/sgl-project/sglang/issues"
+
+[tool.setuptools.package-data]
+"sglang" = [
+    "srt/layers/moe/fused_moe_triton/configs/*/*.json",
+    "srt/layers/quantization/configs/*.json",
+    "srt/mem_cache/storage/hf3fs/hf3fs_utils.cpp",
+]
+
+[tool.setuptools.packages.find]
+exclude = [
+    "assets*",
+    "benchmark*",
+    "docs*",
+    "dist*",
+    "playground*",
+    "scripts*",
+    "tests*",
+]
+
+[tool.wheel]
+exclude = [
+    "assets*",
+    "benchmark*",
+    "docs*",
+    "dist*",
+    "playground*",
+    "scripts*",
+    "tests*",
+]
+
+[tool.codespell]
+ignore-words-list = "ans, als, hel, boostrap, childs, te, vas, hsa, ment"
+skip = "*.json,*.jsonl,*.patch,*.txt"