20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[CI/Build] build on empty device for better dev experience (#4773)

Browse Source
This commit is contained in:
tomeras91 2024-08-11 23:09:44 +03:00 committed by GitHub
parent c08e2b3086
commit 386087970a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 21 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
requirements-cuda.txt
View File

@ -7,5 +7,5 @@ nvidia-ml-py # for pynvml package
torch == 2.4.0 torch == 2.4.0
# These must be updated alongside torch # These must be updated alongside torch
torchvision == 0.19 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version torchvision == 0.19 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version
xformers == 0.0.27.post2 # Requires PyTorch 2.4.0 xformers == 0.0.27.post2; platform_system == 'Linux' and platform_machine == 'x86_64' # Requires PyTorch 2.4.0
vllm-flash-attn == 2.6.1 # Requires PyTorch 2.4.0 vllm-flash-attn == 2.6.1; platform_system == 'Linux' and platform_machine == 'x86_64' # Requires PyTorch 2.4.0

24
setup.py
View File

@ -61,9 +61,12 @@ envs = load_module_from_path('envs', os.path.join(ROOT_DIR, 'vllm', 'envs.py'))
VLLM_TARGET_DEVICE = envs.VLLM_TARGET_DEVICE VLLM_TARGET_DEVICE = envs.VLLM_TARGET_DEVICE
# vLLM only supports Linux platform if not sys.platform.startswith("linux"):
assert sys.platform.startswith( logger.warning(
"linux"), "vLLM only supports Linux platform (including WSL)." "vLLM only supports Linux platform (including WSL). "
"Building on %s, "
"so vLLM may not be able to run correctly", sys.platform)
VLLM_TARGET_DEVICE = "empty"
MAIN_CUDA_VERSION = "12.1" MAIN_CUDA_VERSION = "12.1"
@ -231,6 +234,10 @@ class cmake_build_ext(build_ext):
subprocess.check_call(["cmake", *build_args], cwd=self.build_temp) subprocess.check_call(["cmake", *build_args], cwd=self.build_temp)
def _no_device() -> bool:
return VLLM_TARGET_DEVICE == "empty"
def _is_cuda() -> bool: def _is_cuda() -> bool:
has_cuda = torch.version.cuda is not None has_cuda = torch.version.cuda is not None
return (VLLM_TARGET_DEVICE == "cuda" and has_cuda return (VLLM_TARGET_DEVICE == "cuda" and has_cuda
@ -350,7 +357,9 @@ def find_version(filepath: str) -> str:
def get_vllm_version() -> str: def get_vllm_version() -> str:
version = find_version(get_path("vllm", "version.py")) version = find_version(get_path("vllm", "version.py"))
if _is_cuda(): if _no_device():
version += "+empty"
elif _is_cuda():
cuda_version = str(get_nvcc_cuda_version()) cuda_version = str(get_nvcc_cuda_version())
if cuda_version != MAIN_CUDA_VERSION: if cuda_version != MAIN_CUDA_VERSION:
cuda_version_str = cuda_version.replace(".", "")[:3] cuda_version_str = cuda_version.replace(".", "")[:3]
@ -404,7 +413,9 @@ def get_requirements() -> List[str]:
resolved_requirements.append(line) resolved_requirements.append(line)
return resolved_requirements return resolved_requirements
if _is_cuda(): if _no_device():
requirements = _read_requirements("requirements-cuda.txt")
elif _is_cuda():
requirements = _read_requirements("requirements-cuda.txt") requirements = _read_requirements("requirements-cuda.txt")
cuda_major, cuda_minor = torch.version.cuda.split(".") cuda_major, cuda_minor = torch.version.cuda.split(".")
modified_requirements = [] modified_requirements = []
@ -453,6 +464,9 @@ if envs.VLLM_USE_PRECOMPILED:
ext_modules = [] ext_modules = []
package_data["vllm"].append("*.so") package_data["vllm"].append("*.so")
if _no_device():
ext_modules = []
setup( setup(
name="vllm", name="vllm",
version=get_vllm_version(), version=get_vllm_version(),