CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-06 09:46:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

clip : use FA (#16837)

Browse Source 
* clip : use FA

* cont : add warning about unsupported ops

* implement "auto" mode for clip flash attn

* clip : print more detailed op support info during warmup

* cont : remove obsolete comment [no ci]

* improve debugging message

* trailing space

* metal : remove stray return

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
This commit is contained in:
Georgi Gerganov
2025-11-02 22:21:48 +02:00
committed by GitHub
parent cd5e3b5754
commit 2f966b8ed8
9 changed files with 194 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/test-backend-ops.cpp
View File

@@ -7225,8 +7225,8 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_pad_ext(GGML_TYPE_F32, {11, 22, 33, 44}, 1, 2, 3, 4, 5, 6, 7, 8, v));
}
for (int hsk : { 40, 64, 80, 96, 128, 192, 256, 576 }) {
for (int hsv : { 40, 64, 80, 96, 128, 192, 256, 512 }) {
for (int hsk : { 40, 64, 72, 80, 96, 128, 192, 256, 576 }) {
for (int hsv : { 40, 64, 72, 80, 96, 128, 192, 256, 512 }) {
if (hsk != 192 && hsk != 576 && hsk != hsv) continue;
if (hsk == 192 && (hsv != 128 && hsv != 192)) continue;
if (hsk == 576 && hsv != 512) continue; // DeepSeek MLA