xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-13 18:25:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bug] Fix cpu disable shared_experts VLLM_DISABLE_SHARED_EXPERTS_STREAM (#28157)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye 2025-11-05 20:03:09 -05:00 committed by GitHub
parent b6a248bdd7
commit d79d9f0780
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/platforms/cpu.py
View File

@ -299,7 +299,7 @@ class CpuPlatform(Platform):
os.environ["TORCHINDUCTOR_COMPILE_THREADS"] = "1" os.environ["TORCHINDUCTOR_COMPILE_THREADS"] = "1"
# Disable multi-stream for shared experts as no Stream on CPU # Disable multi-stream for shared experts as no Stream on CPU
os.environ["VLLM_DISABLE_SHARED_EXPERTS_STREAM"] = "0" os.environ["VLLM_DISABLE_SHARED_EXPERTS_STREAM"] = "1"
# Intel OpenMP setting # Intel OpenMP setting
ld_preload_str = os.getenv("LD_PRELOAD", "") ld_preload_str = os.getenv("LD_PRELOAD", "")