A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 6, 13:15 UTC
[Bugfix] Avoid OpenMP thread reallocation in CPU torch compile (#37391)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Li, Jiang committed
Mar 18, 2026 at 15:51 UTC
261801242f481e344a9816222c3c942cf4fd30cb
1 file changed
+1
vllm/platforms/cpu.py
+1
@@ -246,6 +246,7 @@ class CpuPlatform(Platform):
246
"size_asserts": False,
247
"nan_asserts": False,
248
"epilogue_fusion": True,
249
+ "cpp.dynamic_threads": True,
250
}
251
)
252