DeepSeek/DeepGEMM
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepGEMM synced 2025-06-26 23:15:49 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix typo

Browse Source
This commit is contained in:
dotrail 2025-02-27 11:53:33 +00:00
parent 6da94d2d36
commit 488b5fc467
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
deep_gemm/include/deep_gemm/fp8_gemm.cuh
View File

@ -109,7 +109,7 @@ fp8_gemm_kernel(__nv_bfloat16* gmem_d, float* scales_b, int* grouped_layout,
} }
// Initialize barriers // Initialize barriers
DG_STATIC_ASSERT(kNumTMAMulticast <= 32, "To many TMA multicast"); DG_STATIC_ASSERT(kNumTMAMulticast <= 32, "Too many TMA multicast");
if (threadIdx.x == kNumMathThreads) { if (threadIdx.x == kNumMathThreads) {
#pragma unroll #pragma unroll
for (int i = 0; i < kNumStages; ++ i) { for (int i = 0; i < kNumStages; ++ i) {