Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-18 16:55:05 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/master' into gpu-sampling

Browse Source
This commit is contained in:
Daniel Bevenius
2025-11-25 08:20:50 +01:00
parent 0f17ccdee7 b1846f1c8e
commit 53dca56d9b
6 changed files with 213 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-backend-ops.cpp
+3
View File
@@ -7859,6 +7859,9 @@ 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));
for (int kv : { 4096, 8192, 16384, }) {
for (int hs : { 64, 128, }) {
for (int nr : { 1, 4, }) {