[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
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from typing import Any, Callable, Optional
from typing import Any, Callable, Optional, Union
import torch
@@ -226,7 +226,7 @@ class QuarkW8A8Fp8MoEMethod(QuarkMoEMethod):
expert_load_view: Optional[torch.Tensor] = None,
logical_to_physical_map: Optional[torch.Tensor] = None,
logical_replica_count: Optional[torch.Tensor] = None,
) -> torch.Tensor:
) -> Union[torch.Tensor, tuple[torch.Tensor, torch.Tensor]]:
assert self.fused_experts is None
if enable_eplb:
@@ -390,7 +390,7 @@ class QuarkW4A4MXFp4MoEMethod(QuarkMoEMethod):
expert_load_view: Optional[torch.Tensor] = None,
logical_to_physical_map: Optional[torch.Tensor] = None,
logical_replica_count: Optional[torch.Tensor] = None,
) -> torch.Tensor:
) -> Union[torch.Tensor, tuple[torch.Tensor, torch.Tensor]]:
assert self.fused_experts is None
if enable_eplb: