kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-25 05:02:59 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

fix

Browse Source 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
This commit is contained in:
Xiwen Yu 2025-09-09 17:31:31 +08:00
parent 2c287d58b0
commit 11d603bc84
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
cpp/tensorrt_llm/cutlass_extensions/include/cutlass_extensions/gemm_configs.h
View File

@ -24,6 +24,7 @@
#include "cute/tensor.hpp"
#include "tensorrt_llm/common/assert.h"
#include "tensorrt_llm/common/tllmException.h"
namespace tensorrt_llm
{
@ -425,7 +426,7 @@ struct CutlassGemmConfig
, sm_version(sm_version)
, is_tma_warp_specialized(true)
{
assert(sm_version >= 100 && sm_version < 120 && "Expected SM 10x version");
TLLM_CHECK_WITH_INFO(sm_version >= 100 && sm_version < 120, "Expected SM 10x version");
}
CutlassGemmConfig(CutlassTileConfigSM120 tile_config_sm120, MainloopScheduleType mainloop_schedule,