xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-26 12:57:13 +08:00
Code Issues Packages Projects Releases Wiki Activity

Revert "[Refactor] Fix Compile Warning #1444-D (#21208)" (#21384)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye 2025-07-22 11:22:10 -04:00 committed by GitHub
parent f38ee34a0a
commit 226b452a20
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
csrc/moe/topk_softmax_kernels.cu
View File

@ -20,7 +20,6 @@
#include <ATen/cuda/CUDAContext.h> #include <ATen/cuda/CUDAContext.h>
#include <c10/cuda/CUDAGuard.h> #include <c10/cuda/CUDAGuard.h>
#include "../cuda_compat.h" #include "../cuda_compat.h"
#include <cuda/std/functional>
#ifndef USE_ROCM #ifndef USE_ROCM
#include <cub/util_type.cuh> #include <cub/util_type.cuh>
@ -63,7 +62,7 @@ __launch_bounds__(TPB) __global__
const int thread_row_offset = blockIdx.x * num_cols; const int thread_row_offset = blockIdx.x * num_cols;
cuda::std::plus<float> sum; cub::Sum sum;
float threadData(-FLT_MAX); float threadData(-FLT_MAX);
// Don't touch finished rows. // Don't touch finished rows.