[Bugfix] Fix Stream usage in CPU model runner and OneDNN kernel check (#25046)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
@@ -185,6 +185,11 @@ class CpuPlatform(Platform):
|
||||
parallel_config.distributed_executor_backend = "mp"
|
||||
if parallel_config.worker_cls == "auto":
|
||||
parallel_config.worker_cls = "vllm.v1.worker.cpu_worker.CPUWorker"
|
||||
# Disable DBO
|
||||
if parallel_config.enable_dbo:
|
||||
logger.warning(
|
||||
"Dual-Batch Overlap is not supported on CPU, disabled.")
|
||||
parallel_config.enable_dbo = False
|
||||
|
||||
# Note: workaround for v1 gpu_model_runner
|
||||
from vllm.config import CompilationLevel
|
||||
|
||||
Reference in New Issue
Block a user