[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
@@ -223,7 +223,7 @@ if has_deep_ep() and not current_platform.has_device_capability(100):
|
||||
)
|
||||
|
||||
if has_mori():
|
||||
from vllm.model_executor.layers.fused_moe.mori_prepare_finalize import (
|
||||
from vllm.model_executor.layers.fused_moe.prepare_finalize.mori import (
|
||||
MoriPrepareAndFinalize,
|
||||
)
|
||||
|
||||
|
||||
@@ -10,10 +10,12 @@ from vllm.model_executor.layers.fused_moe.experts.batched_deep_gemm_moe import (
|
||||
BatchedDeepGemmExperts,
|
||||
)
|
||||
from vllm.model_executor.layers.fused_moe.fused_batched_moe import (
|
||||
BatchedPrepareAndFinalize,
|
||||
BatchedTritonExperts,
|
||||
)
|
||||
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.utils.deep_gemm import calc_diff, is_deep_gemm_supported
|
||||
|
||||
from .test_deepgemm import make_block_quant_fp8_weights
|
||||
|
||||
@@ -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