Skip to content

cuda : fix argsort with 64k+ rows #16849

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 30, 2025
Merged

cuda : fix argsort with 64k+ rows #16849

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions ggml/src/ggml-cuda/argsort.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,7 +87,7 @@ template<ggml_sort_order order>
static __global__ void k_argsort_f32_i32(const float * x, int * dst, const int ncols, int ncols_pad) {
// bitonic sort
int col = threadIdx.x;
int row = blockIdx.y;
int row = blockIdx.x;

if (col >= ncols_pad) {
return;
Expand Down Expand Up @@ -151,7 +151,7 @@ static void argsort_f32_i32_cuda_bitonic(const float * x,
const int ncols_pad = next_power_of_2(ncols);

const dim3 block_dims(ncols_pad, 1, 1);
const dim3 block_nums(1, nrows, 1);
const dim3 block_nums(nrows, 1, 1);
const size_t shared_mem = ncols_pad * sizeof(int);

// FIXME: this limit could be raised by ~2-4x on Ampere or newer
Expand Down
3 changes: 2 additions & 1 deletion tests/test-backend-ops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7039,7 +7039,8 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {16, 10, 10, 10}, order));
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {60, 10, 10, 10}, order)); // qwen
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {1024, 1, 1, 1}, order));
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {16384, 1, 1, 1}, order)); // bailingmoe2 (group selection)
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {16384, 1, 1, 1}, order)); // many backends only handle up to 1024
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {2, 8, 8192, 1}, order)); // bailingmoe2 (group selection)
}

for (ggml_scale_mode mode : {GGML_SCALE_MODE_NEAREST, GGML_SCALE_MODE_BILINEAR}) {
Expand Down
Loading