fused rmsnorm quant fp8 work

python/pyproject.toml

@@ -10,141 +10,141 @@ readme = "README.md"
 requires-python = ">=3.10"
 license = { file = "LICENSE" }
 classifiers = [
-  "Programming Language :: Python :: 3",
-  "License :: OSI Approved :: Apache Software License",
-]
-dependencies = [
-  "IPython",
-  "aiohttp",
-  "anthropic>=0.20.0",
-  "blobfile==3.0.0",
-  "build",
-  "compressed-tensors",
-  "cuda-python",
-  "datasets",
-  "einops",
-  "fastapi",
-  "flashinfer_python==0.4.0",
-  "hf_transfer",
-  "huggingface_hub",
-  "interegular",
-  "llguidance>=0.7.11,<0.8.0",
-  "modelscope",
-  "msgspec",
-  "ninja",
-  "numpy",
-  "nvidia-cutlass-dsl==4.2.1",
-  "openai-harmony==0.0.4",
-  "openai==1.99.1",
-  "orjson",
-  "outlines==0.1.11",
-  "packaging",
-  "partial_json_parser",
-  "pillow",
-  "prometheus-client>=0.20.0",
-  "psutil",
-  "py-spy",
-  "pybase64",
-  "pydantic",
-  "nvidia-ml-py",
-  "python-multipart",
-  "pyzmq>=25.1.2",
-  "requests",
-  "scipy",
-  "sentencepiece",
-  "setproctitle",
-  "sgl-kernel==0.3.15",
-  "soundfile==0.13.1",
-  "tiktoken",
-  "timm==1.0.16",
-  "torch==2.8.0",
-  "torch_memory_saver==0.0.9rc2",
-  "torchao==0.9.0",
-  "torchaudio==2.8.0",
-  "torchvision",
-  "tqdm",
-  "transformers==4.57.1",
-  "uvicorn",
-  "uvloop",
-  "xgrammar==0.1.25",
-  "grpcio==1.75.1", # keep it align with compile_proto.py
-  "grpcio-tools==1.75.1", # keep it align with compile_proto.py
-  "grpcio-reflection==1.75.1", # required by srt/entrypoints/grpc_server.py
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: Apache Software License",
 ]
+dependencies = ["aiohttp", "requests", "tqdm", "numpy", "IPython", "setproctitle"]
 
 [project.optional-dependencies]
-decord = ["decord2"]
-test = [
-  "accelerate",
-  "expecttest",
-  "gguf",
-  "jsonlines",
-  "matplotlib",
-  "pandas",
-  "peft",
-  "pytest",
-  "sentence_transformers",
-  "tabulate",
+runtime_common = [
+    "blobfile==3.0.0",
+    "build",
+    "compressed-tensors",
+    "datasets",
+    "einops",
+    "fastapi",
+    "hf_transfer",
+    "huggingface_hub",
+    "interegular",
+    "llguidance>=0.7.11,<0.8.0",
+    "modelscope",
+    "msgspec",
+    "ninja",
+    "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",
+    "pynvml",
+    "python-multipart",
+    "pyzmq>=25.1.2",
+    "scipy",
+    "sentencepiece",
+    "soundfile==0.13.1",
+    "timm==1.0.16",
+    "tiktoken",
+    "torchao==0.9.0",
+    "transformers==4.57.1",
+    "uvicorn",
+    "uvloop",
+    "xgrammar==0.1.25",
 ]
+
 tracing = [
-  "opentelemetry-api",
-  "opentelemetry-exporter-otlp",
-  "opentelemetry-exporter-otlp-proto-grpc",
-  "opentelemetry-sdk",
+    "opentelemetry-sdk",
+    "opentelemetry-api",
+    "opentelemetry-exporter-otlp",
+    "opentelemetry-exporter-otlp-proto-grpc",
 ]
-all = ["sglang[test]", "sglang[decord]"]
-cu130 = [
-  "torch==2.9.0",
-  "torchaudio==2.9.0",
-  "torchvision==0.24.0",
+
+srt = [
+    "sglang[runtime_common]",
+    "sgl-kernel==0.3.15",
+    "torch==2.8.0",
+    "torchaudio==2.8.0",
+    "torchvision",
+    "cuda-python",
+    "flashinfer_python==0.4.0",
 ]
-cu130_all = [
-  "sglang[test]",
-  "sglang[decord]",
-  "sglang[cu130]"
+
+# HIP (Heterogeneous-computing Interface for Portability) for AMD
+# => base docker rocm/vllm-dev:20250114, not from public vllm whl
+srt_hip = [
+    "sglang[runtime_common]",
+    "torch",
+    "petit_kernel==0.0.2",
+    "wave-lang==3.7.0",
 ]
 
+# https://docs.sglang.ai/platforms/ascend_npu.html
+srt_npu = ["sglang[runtime_common]"]
+
+# For Intel Gaudi(device : hpu) follow the installation guide
+# https://docs.vllm.ai/en/latest/getting_started/gaudi-installation.html
+srt_hpu = ["sglang[runtime_common]"]
 
-# The following will be deprecated in 2 weeks
-dev = ["sglang[test]", "sglang[decord]"]
-all_aarch64 = ["sglang[test]"]
-blackwell = ["sglang[test]", "sglang[decord]"]
-blackwell_aarch64 = ["sglang[test]"]
+openai = ["openai==1.99.1", "tiktoken"]
+anthropic = ["anthropic>=0.20.0"]
+litellm = ["litellm>=1.0.0"]
+torch_memory_saver = ["torch_memory_saver==0.0.9rc1"]
+decord = ["decord"]
+test = [
+    "accelerate",
+    "expecttest",
+    "jsonlines",
+    "matplotlib",
+    "pandas",
+    "peft",
+    "sentence_transformers",
+    "pytest",
+    "tabulate",
+]
+all = ["sglang[srt]", "sglang[openai]", "sglang[anthropic]", "sglang[torch_memory_saver]", "sglang[decord]"]
+all_hip = ["sglang[srt_hip]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
+all_hpu = ["sglang[srt_hpu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
+all_npu = ["sglang[srt_npu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
 
+dev = ["sglang[all]", "sglang[test]"]
+dev_hip = ["sglang[all_hip]", "sglang[test]"]
+dev_hpu = ["sglang[all_hpu]", "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",
-  "srt/speculative/cpp_ngram/*.cpp",
-  "srt/speculative/cpp_ngram/*.h",
+    "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*",
+    "assets*",
+    "benchmark*",
+    "docs*",
+    "dist*",
+    "playground*",
+    "scripts*",
+    "tests*",
 ]
 
 [tool.wheel]
 exclude = [
-  "assets*",
-  "benchmark*",
-  "docs*",
-  "dist*",
-  "playground*",
-  "scripts*",
-  "tests*",
+    "assets*",
+    "benchmark*",
+    "docs*",
+    "dist*",
+    "playground*",
+    "scripts*",
+    "tests*",
 ]
 
 [tool.codespell]