happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Apply automated code-formating to softmax.cu

This commit is contained in:
Oliver Simons 2025-12-15 11:05:17 +01:00
parent 3732b85b09
commit e5737f665f
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/softmax.cu
View File

@ -419,7 +419,9 @@ static void soft_max_f32_cuda(const float * x,
// Parallelize across SMs for top-p/dist-sampling
// The heuristic for parallelizing rows across SMs vs parallelizing single row & looping over all rows was done on the basis of a B6000 GPU and
// Can be adapted further for lower-SM-count GPUs, though keeping data in registers should be implemented first as that is the optimal solution.
if (ggml_cuda_info().devices[id].supports_cooperative_launch && ncols_x / (params.ne01 * params.ne02 * params.ne03) > 8192 && mask == nullptr && sinks == nullptr && params.scale == 1.0f && params.max_bias == 0.0f) {
if (ggml_cuda_info().devices[id].supports_cooperative_launch &&
ncols_x / (params.ne01 * params.ne02 * params.ne03) > 8192 && mask == nullptr && sinks == nullptr &&
params.scale == 1.0f && params.max_bias == 0.0f) {
ggml_cuda_pool_alloc<float> tmp_maxs_alloc(ctx.pool(), ggml_cuda_info().devices[id].nsm * sizeof(float));
ggml_cuda_pool_alloc<float> tmp_sums_alloc(ctx.pool(), ggml_cuda_info().devices[id].nsm * sizeof(float));