[MoE] Move remaining PrepareAndFinalize to prepare finalize folder (#39009)
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com> Signed-off-by: Jackmin801 <ongjackm@gmail.com> Co-authored-by: Robert Shaw <robertgshaw2@gmail.com>
This commit is contained in:
co-authored by
Robert Shaw
parent
ff2c2bd80a
commit
447c372ac5
@@ -18,7 +18,6 @@ from vllm.model_executor.layers.fused_moe.config import (
|
||||
RoutingMethodType,
|
||||
)
|
||||
from vllm.model_executor.layers.fused_moe.fused_batched_moe import (
|
||||
BatchedPrepareAndFinalize,
|
||||
BatchedTritonExperts,
|
||||
NaiveBatchedExperts,
|
||||
)
|
||||
@@ -27,6 +26,9 @@ from vllm.model_executor.layers.fused_moe.fused_moe import (
|
||||
fused_experts,
|
||||
)
|
||||
from vllm.model_executor.layers.fused_moe.modular_kernel import FusedMoEKernel
|
||||
from vllm.model_executor.layers.fused_moe.prepare_finalize.batched import (
|
||||
BatchedPrepareAndFinalize,
|
||||
)
|
||||
from vllm.model_executor.layers.fused_moe.router.fused_topk_router import fused_topk
|
||||
from vllm.model_executor.layers.fused_moe.utils import moe_kernel_quantize_input
|
||||
from vllm.utils.deep_gemm import per_block_cast_to_fp8
|
||||
|
||||
Reference in New Issue
Block a user