[Distributed] Enable custom all-reduce under VLLM_BATCH_INVARIANT (#58623)
Signed-off-by: Flora Feng <4florafeng@gmail.com> Signed-off-by: sfeng33 <4florafeng@gmail.com>
This commit is contained in:
@@ -1087,10 +1087,6 @@ class ParallelConfig:
|
||||
# Lazy import to avoid circular import
|
||||
from vllm.v1.executor import Executor
|
||||
|
||||
# Enable batch invariance settings if requested
|
||||
if envs.VLLM_BATCH_INVARIANT:
|
||||
self.disable_custom_all_reduce = True
|
||||
|
||||
if (
|
||||
self.distributed_executor_backend is not None
|
||||
and not isinstance(self.distributed_executor_backend, str)
|
||||
|
||||
Reference in New Issue
Block a user