[Kernels] Overlap shared experts with send/recv (#23273)

Signed-off-by: Bill Nell <bnell@redhat.com>
This commit is contained in:
bnellnm
2025-09-03 12:35:18 -04:00
committed by GitHub
parent fa4311d85f
commit e9b92dcd89
32 changed files with 885 additions and 227 deletions

View File

@@ -1,6 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from typing import TYPE_CHECKING, Any
from typing import Any
import torch
import torch.distributed as dist
@@ -13,11 +13,6 @@ from .base_device_communicator import All2AllManagerBase, Cache
logger = init_logger(__name__)
if TYPE_CHECKING:
from vllm.model_executor.layers.fused_moe.layer import FusedMoE
else:
FusedMoE = None
class NaiveAll2AllManager(All2AllManagerBase):
"""