kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-13 22:18:36 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

replace std::min with min inside CUDA kernel

Browse Source
This commit is contained in:
Will Yu 2024-08-23 15:11:37 +08:00
parent ca34331e98
commit 6dfa8df479
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/customAllReduceKernels.cu
View File

@ -612,7 +612,7 @@ static __global__ void oneShotAllReduceKernel(AllReduceParams params)
// Start and end offsets of the thread
size_t const chunk_start = bidx * params.elts_per_block + tidx * PACKED_ELTS;
size_t const chunk_end = std::min((bidx + 1) * params.elts_per_block, params.elts_total);
size_t const chunk_end = min((bidx + 1) * params.elts_per_block, params.elts_total);
T* buffers[RANKS_PER_NODE];
#pragma unroll