obscura/vllm
2
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2026-06-06 00:16:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

[MoE Refactor] Move remaining experts classes to experts directory (#42334)

Browse Source 
Signed-off-by: Bill Nell <bnell@redhat.com>
This commit is contained in:
bnellnm
2026-05-12 09:19:46 -04:00
committed by GitHub
parent 206eaed08d
commit 6427603ae8
26 changed files with 48 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmarks/kernels/benchmark_moe.py
+2 -2
View File
@@ -27,10 +27,10 @@ from vllm.model_executor.layers.fused_moe.config import (
RoutingMethodType,
_get_config_dtype_str,
)
from vllm.model_executor.layers.fused_moe.fused_moe import *
from vllm.model_executor.layers.fused_moe.triton_deep_gemm_moe import (
from vllm.model_executor.layers.fused_moe.experts.triton_deep_gemm_moe import (
TritonOrDeepGemmExperts,
)
from vllm.model_executor.layers.fused_moe.fused_moe import *
from vllm.transformers_utils.config import get_config
from vllm.triton_utils import triton
from vllm.utils.argparse_utils import FlexibleArgumentParser