sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 114 Packages Projects Releases Wiki Activity

vulkan: support flash attention GQA/split_k with small batches (#18938)

Browse Source
This commit is contained in:
Jeff Bolz
2026-01-21 10:43:43 -06:00
committed by GitHub
parent 067b8d7af3
commit 33f890e579
7 changed files with 74 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-backend-ops.cpp
+3
View File
@@ -8460,6 +8460,9 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
// Qwen3-VL-8B https://github.com/ggml-org/llama.cpp/issues/17012
test_cases.emplace_back(new test_flash_attn_ext(72, 72, 16, {1, 1}, 5776, 5776, false, false, 0, 0, GGML_PREC_F32, GGML_TYPE_F16));
test_cases.emplace_back(new test_flash_attn_ext(64, 64, 8, {8, 1}, 7680, 1, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_F16));
test_cases.emplace_back(new test_flash_attn_ext(64, 64, 8, {8, 1}, 7680, 4, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_F16));
for (int kv : { 4096, 8192, 16384, }) {
for (int hs : { 64, 128, }) {
for (int nr : { 1, 4, }) {