upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-06 18:10:51 -05:00
Code Issues Packages Projects Releases Wiki Activity

Fix compiler warnings by casting const away

Browse Source
This commit is contained in:
Oliver Simons
2025-12-09 13:05:43 +01:00
parent 886c3668b5
commit 07003f1ffb
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/softmax.cu
View File

@@ -411,7 +411,7 @@ static void soft_max_f32_cuda(const float * x,
if (ggml_cuda_info().devices[id].supports_cooperative_launch) {
ggml_cuda_pool_alloc<float> tmp_alloc(ctx.pool(), ggml_cuda_info().devices[id].nsm * sizeof(float));
void * kernel_args[] = { (void *) &x, (void *) &dst, (void *) &tmp_alloc.ptr, (void *) &params };
void * kernel_args[] = { (void *) &x, (void *) &dst, (void *) &tmp_alloc.ptr, (void *) const_cast<soft_max_params *>(& params)};
CUDA_CHECK(cudaLaunchCooperativeKernel((void *) soft_max_f32_parallelize_cols,
dim3(ggml_cuda_info().devices[id].nsm, 1, 1),
dim3(WARP_SIZE * 8, 1, 1), kernel_args, 0, stream));