kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

GEMM+AR TP2 harness fix (#6027)

Browse Source
This commit is contained in:
xavier-nvidia 2025-07-14 15:52:53 -07:00 committed by GitHub
parent 60538df1b5
commit ac0b3f8b66
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
cpp/tensorrt_llm/kernels/cutlass_kernels/allreduce_gemm/communication/sm90_allreduce_nvls_warpspecialized.hpp
View File

@ -201,7 +201,7 @@ public:
auto [M, N, K, L] = problem_shape;
auto [m, n, k, l] = tile_coord;
if (!tile_valid(m, n) || params_ptr->world_size <= 2)
if (!tile_valid(m, n) || params_ptr->world_size <= 1)
{
return; // nothing to do
}