### What this PR does / why we need it? On Arm systems, os.sched_yield() does not take effect, causing the GIL (Global Interpreter Lock) to remain unrelinquished and resulting in CPU bound issues. This PR applies a patch to sched_yield in vLLM, making the process execute time.sleep(0) instead to release the GIL. ### Does this PR introduce _any_ user-facing change? Signed-off-by: fems14 <1804143737@qq.com> Co-authored-by: fems14 <74094523+fems14@users.noreply.github.com>
14 lines
367 B
Python
14 lines
367 B
Python
import sys
|
|
|
|
import vllm.distributed.utils
|
|
from vllm.platforms import CpuArchEnum, Platform
|
|
|
|
is_arm = (Platform.get_cpu_architecture() == CpuArchEnum.ARM)
|
|
|
|
USE_SCHED_YIELD = (
|
|
((sys.version_info[:3] >= (3, 11, 1)) or
|
|
(sys.version_info[:2] == (3, 10) and sys.version_info[2] >= 8))
|
|
and not is_arm)
|
|
|
|
vllm.distributed.utils.USE_SCHED_YIELD = USE_SCHED_YIELD
|