CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

cuda : fix argsort with 64k+ rows (#16849)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2025-10-30 08:56:28 +01:00
committed by GitHub
parent d7395115ba
commit 229bf68628
2 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -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;
@@ -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

3
tests/test-backend-ops.cpp
View File

@@ -7111,7 +7111,8 @@ 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}) {