Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Commit776ba60

Browse files
committed
fix
Signed-off-by: Yifei Zhang <219273404+yifeizhang-c@users.noreply.github.com>
1 parent3af9d0a commit776ba60

File tree

1 file changed

+1
-0
lines changed

1 file changed

+1
-0
lines changed

‎tensorrt_llm/_torch/modules/fused_moe/fused_moe_wide_ep.py‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -250,6 +250,7 @@ def _check_configs(self):
250250
defselect_alltoall_method_type(mapping:Mapping,top_k:int,
251251
dtype:torch.dtype,
252252
use_cuda_graph:bool)->AlltoallMethodType:
253+
253254
defis_deepep_feasible(num_ranks:int)->bool:
254255
num_rdma_ranks=num_ranks//8# 8 is the number of NVL peers
255256
returnnum_ranksin [2,4,8]ornum_rdma_ranksin [2,4,8,16]

0 commit comments

Comments
 (0)

[8]ページ先頭

©2009-2025 Movatter.jp