[MoE] Move various experts classes to fused_moe/experts/ (#41979)

Signed-off-by: Jackmin801 <ongjackm@gmail.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Signed-off-by: Jackmin801 <56836461+Jackmin801@users.noreply.github.com>
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Jackmin801 <ongjackm@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Jackmin801 <56836461+Jackmin801@users.noreply.github.com>
This commit is contained in:
bnellnm
2026-05-11 07:54:33 +08:00
committed by GitHub
co-authored by Jackmin801 Claude Robert Shaw Robert Shaw Jackmin801
parent 21943d4c25
commit 1b57eb41f2
34 changed files with 586 additions and 553 deletions
+3 -3
View File
@@ -18,12 +18,12 @@ from vllm.model_executor.layers.fused_moe.config import (
RoutingMethodType,
fp8_w8a8_moe_quant_config,
)
from vllm.model_executor.layers.fused_moe.experts.flashinfer_cutlass_moe import (
FlashInferExperts,
)
from vllm.model_executor.layers.fused_moe.experts.trtllm_fp8_moe import (
TrtLlmFp8ExpertsMonolithic,
)
from vllm.model_executor.layers.fused_moe.flashinfer_cutlass_moe import (
FlashInferExperts,
)
from vllm.model_executor.layers.fused_moe.fused_moe import fused_experts
from vllm.model_executor.layers.quantization.utils.flashinfer_utils import (
rotate_weights_for_fi_trtllm_fp8_per_tensor_moe,