vllm/setup.py

187 lines
6.6 KiB
Python

import io
import os
import re
import subprocess
from typing import List, Set
from packaging.version import parse, Version
import setuptools
import torch
from torch.utils.cpp_extension import BuildExtension, CUDAExtension, CUDA_HOME
ROOT_DIR = os.path.dirname(__file__)
# Compiler flags.
CXX_FLAGS = ["-g", "-O2", "-std=c++17"]
# TODO(woosuk): Should we use -O3?
NVCC_FLAGS = ["-O2", "-std=c++17"]
ABI = 1 if torch._C._GLIBCXX_USE_CXX11_ABI else 0
CXX_FLAGS += [f"-D_GLIBCXX_USE_CXX11_ABI={ABI}"]
NVCC_FLAGS += [f"-D_GLIBCXX_USE_CXX11_ABI={ABI}"]
if CUDA_HOME is None:
raise RuntimeError(
f"Cannot find CUDA_HOME. CUDA must be available to build the package.")
def get_nvcc_cuda_version(cuda_dir: str) -> Version:
"""Get the CUDA version from nvcc.
Adapted from https://github.com/NVIDIA/apex/blob/8b7a1ff183741dd8f9b87e7bafd04cfde99cea28/setup.py
"""
nvcc_output = subprocess.check_output([cuda_dir + "/bin/nvcc", "-V"],
universal_newlines=True)
output = nvcc_output.split()
release_idx = output.index("release") + 1
nvcc_cuda_version = parse(output[release_idx].split(",")[0])
return nvcc_cuda_version
# Collect the compute capabilities of all available GPUs.
device_count = torch.cuda.device_count()
compute_capabilities: Set[int] = set()
for i in range(device_count):
major, minor = torch.cuda.get_device_capability(i)
if major < 7:
raise RuntimeError(
"GPUs with compute capability less than 7.0 are not supported.")
compute_capabilities.add(major * 10 + minor)
# Validate the NVCC CUDA version.
nvcc_cuda_version = get_nvcc_cuda_version(CUDA_HOME)
if nvcc_cuda_version < Version("11.0"):
raise RuntimeError("CUDA 11.0 or higher is required to build the package.")
if 86 in compute_capabilities and nvcc_cuda_version < Version("11.1"):
raise RuntimeError(
"CUDA 11.1 or higher is required for GPUs with compute capability 8.6.")
if 89 in compute_capabilities and nvcc_cuda_version < Version("11.8"):
# CUDA 11.8 is required to generate the code targeting compute capability 8.9.
# However, GPUs with compute capability 8.9 can also run the code generated by
# the previous versions of CUDA 11 and targeting compute capability 8.0.
# Therefore, if CUDA 11.8 is not available, we target compute capability 8.0
# instead of 8.9.
compute_capabilities.remove(89)
compute_capabilities.add(80)
if 90 in compute_capabilities and nvcc_cuda_version < Version("11.8"):
raise RuntimeError(
"CUDA 11.8 or higher is required for GPUs with compute capability 9.0.")
# If no GPU is available, add all supported compute capabilities.
if not compute_capabilities:
compute_capabilities = {70, 75, 80}
if nvcc_cuda_version >= Version("11.1"):
compute_capabilities.add(86)
if nvcc_cuda_version >= Version("11.8"):
compute_capabilities.add(89)
compute_capabilities.add(90)
# Add target compute capabilities to NVCC flags.
for capability in compute_capabilities:
NVCC_FLAGS += ["-gencode", f"arch=compute_{capability},code=sm_{capability}"]
# Use NVCC threads to parallelize the build.
if nvcc_cuda_version >= Version("11.2"):
num_threads = min(os.cpu_count(), 8)
NVCC_FLAGS += ["--threads", str(num_threads)]
ext_modules = []
# Cache operations.
cache_extension = CUDAExtension(
name="vllm.cache_ops",
sources=["csrc/cache.cpp", "csrc/cache_kernels.cu"],
extra_compile_args={"cxx": CXX_FLAGS, "nvcc": NVCC_FLAGS},
)
ext_modules.append(cache_extension)
# Attention kernels.
attention_extension = CUDAExtension(
name="vllm.attention_ops",
sources=["csrc/attention.cpp", "csrc/attention/attention_kernels.cu"],
extra_compile_args={"cxx": CXX_FLAGS, "nvcc": NVCC_FLAGS},
)
ext_modules.append(attention_extension)
# Positional encoding kernels.
positional_encoding_extension = CUDAExtension(
name="vllm.pos_encoding_ops",
sources=["csrc/pos_encoding.cpp", "csrc/pos_encoding_kernels.cu"],
extra_compile_args={"cxx": CXX_FLAGS, "nvcc": NVCC_FLAGS},
)
ext_modules.append(positional_encoding_extension)
# Layer normalization kernels.
layernorm_extension = CUDAExtension(
name="vllm.layernorm_ops",
sources=["csrc/layernorm.cpp", "csrc/layernorm_kernels.cu"],
extra_compile_args={"cxx": CXX_FLAGS, "nvcc": NVCC_FLAGS},
)
ext_modules.append(layernorm_extension)
# Activation kernels.
activation_extension = CUDAExtension(
name="vllm.activation_ops",
sources=["csrc/activation.cpp", "csrc/activation_kernels.cu"],
extra_compile_args={"cxx": CXX_FLAGS, "nvcc": NVCC_FLAGS},
)
ext_modules.append(activation_extension)
def get_path(*filepath) -> str:
return os.path.join(ROOT_DIR, *filepath)
def find_version(filepath: str):
"""Extract version information from the given filepath.
Adapted from https://github.com/ray-project/ray/blob/0b190ee1160eeca9796bc091e07eaebf4c85b511/python/setup.py
"""
with open(filepath) as fp:
version_match = re.search(
r"^__version__ = ['\"]([^'\"]*)['\"]", fp.read(), re.M)
if version_match:
return version_match.group(1)
raise RuntimeError("Unable to find version string.")
def read_readme() -> str:
"""Read the README file."""
return io.open(get_path("README.md"), "r", encoding="utf-8").read()
def get_requirements() -> List[str]:
"""Get Python package dependencies from requirements.txt."""
with open(get_path("requirements.txt")) as f:
requirements = f.read().strip().split("\n")
return requirements
setuptools.setup(
name="vllm",
version=find_version(get_path("vllm", "__init__.py")),
author="vLLM Team",
license="Apache 2.0",
description="A high-throughput and memory-efficient inference and serving engine for LLMs",
long_description=read_readme(),
long_description_content_type="text/markdown",
url="https://github.com/vllm-project/vllm",
project_urls={
"Homepage": "https://github.com/vllm-project/vllm",
"Documentation": "https://vllm.readthedocs.io/en/latest/",
},
classifiers=[
"Programming Language :: Python :: 3.8",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"License :: OSI Approved :: Apache Software License",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
],
packages=setuptools.find_packages(
exclude=("assets", "benchmarks", "csrc", "docs", "examples", "tests")),
python_requires=">=3.8",
install_requires=get_requirements(),
ext_modules=ext_modules,
cmdclass={"build_ext": BuildExtension},
)