biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Feature]: Remove Chunking From FusedMoE (#34086)

Browse Source 
Signed-off-by: SouthWest7 <am1ao@qq.com>
Signed-off-by: Southwest <1403572259@qq.com>
Signed-off-by: southwest <am1ao@qq.com>
Signed-off-by: Xinan Miao <1403572259@qq.com>
Co-authored-by: SouthWest7 <am1ao@qq.com>
This commit is contained in:
Xinan Miao
2026-03-13 02:24:38 +08:00
committed by GitHub
parent c973ecdead
commit 2cdf92228c
28 changed files with 152 additions and 523 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/kernels/moe/modular_kernel_tools/cli_args.py
View File

@@ -82,11 +82,6 @@ def make_config_arg_parser(description: str):
"--num-experts", type=int, default=32, help="Global num experts"
)
parser.add_argument("--topk", nargs="+", type=int, default=[4, 1], help="num topk")
parser.add_argument(
"--fused-moe-chunk-size",
type=int,
help="Fused moe chunk size used for the non-batched fused experts impl.",
)
# Quant args
parser.add_argument(
@@ -158,7 +153,6 @@ def make_config(args: argparse.Namespace) -> Config:
quant_config=quant_config,
prepare_finalize_type=args.pf_type,
fused_experts_type=args.experts_type,
fused_moe_chunk_size=args.fused_moe_chunk_size,
world_size=args.world_size,
torch_trace_dir_path=args.torch_trace_dir_path,
)