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 10, 20:15 UTC
[CPU] Disable async schedule on CPU (#31525)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Li, Jiang committed
Dec 30, 2025 at 20:34 UTC
7157596103666ee7ccb7008acee8bff8a8ff1731
1 file changed
+2
vllm/platforms/cpu.py
+2
@@ -193,6 +193,8 @@ class CpuPlatform(Platform):
193
)
194
195
scheduler_config = vllm_config.scheduler_config
196
+ # async scheduling is not required on CPU
197
+ scheduler_config.async_scheduling = False
198
if (
199
scheduler_config.enable_chunked_prefill
200
or cache_config.enable_prefix_caching