frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix][Kernel] Promote another index to int64_t (#6838)

Browse Source
This commit is contained in:
Tyler Michael Smith
2024-07-26 14:41:04 -04:00
committed by GitHub
parent 07278c37dd
commit 50704f52c4
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
csrc/quantization/fp8/common.cu
View File

@ -48,7 +48,7 @@ __global__ void segmented_max_reduction(float* __restrict__ scale,
const scalar_t* __restrict__ input,
int64_t num_elems) {
__shared__ float cache[1024];
int i = blockDim.x * blockIdx.x + threadIdx.x;
int64_t i = blockDim.x * blockIdx.x + threadIdx.x;
// First store maximum for all values processes by
// the current thread in cache[threadIdx.x]