[cherry-pick]【main】patch sched_yield (#3648) (#3687)

### 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 <[email protected]>
Co-authored-by: fems14 <[email protected]>

Author: wangxiyuan

vllm_ascend/patch/platform/__init__.py

@@ -19,6 +19,7 @@
 import vllm_ascend.patch.platform.patch_config  # noqa
 import vllm_ascend.patch.platform.patch_distributed  # noqa
 import vllm_ascend.patch.platform.patch_mamba_config  # noqa
+import vllm_ascend.patch.platform.patch_sched_yield  # noqa
 
 if os.getenv("DYNAMIC_EPLB", "false") == "true" or os.getenv(
         "EXPERT_MAP_RECORD", "false") == "true":

vllm_ascend/patch/platform/patch_sched_yield.py

@@ -0,0 +1,13 @@
+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

vllm_ascend/patch/worker/__init__.py

@@ -21,6 +21,7 @@
     import vllm_ascend.patch.worker.patch_triton
 
 # isort: off
+import vllm_ascend.patch.platform.patch_sched_yield  # noqa
 import vllm_ascend.patch.worker.patch_distributed  # noqa
 import vllm_ascend.patch.worker.patch_logits  # noqa
 import vllm_ascend.patch.worker.patch_roberta  # noqa