biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[bugfix] Fix auto thread-binding when world_size > 1 in CPU backend and refactor code (#21032)

Browse Source 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
Li, Jiang
2025-07-19 20:13:55 +08:00
committed by GitHub
parent b3d82108e7
commit e3a0e43d7f
7 changed files with 144 additions and 150 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/envs.py
View File

@@ -44,7 +44,7 @@ if TYPE_CHECKING:
VLLM_PP_LAYER_PARTITION: Optional[str] = None
VLLM_CPU_KVCACHE_SPACE: int = 0
VLLM_CPU_OMP_THREADS_BIND: str = ""
VLLM_CPU_NUM_OF_RESERVED_CPU: int = 0
VLLM_CPU_NUM_OF_RESERVED_CPU: Optional[int] = None
VLLM_CPU_MOE_PREPACK: bool = True
VLLM_CPU_SGL_KERNEL: bool = False
VLLM_XLA_CACHE_PATH: str = os.path.join(VLLM_CACHE_ROOT, "xla_cache")
@@ -442,7 +442,8 @@ environment_variables: dict[str, Callable[[], Any]] = {
# (CPU backend only) CPU cores not used by OMP threads .
# Those CPU cores will not be used by OMP threads of a rank.
"VLLM_CPU_NUM_OF_RESERVED_CPU":
lambda: int(os.getenv("VLLM_CPU_NUM_OF_RESERVED_CPU", "0")),
lambda: int(os.getenv("VLLM_CPU_NUM_OF_RESERVED_CPU", "0"))
if "VLLM_CPU_NUM_OF_RESERVED_CPU" in os.environ else None,
# (CPU backend only) whether to use prepack for MoE layer. This will be
# passed to ipex.llm.modules.GatedMLPMOE. On unsupported CPUs, you might