CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : refactor + optimize (#15857)

Browse Source 
* metal : refactor

ggml-ci

* cont : refactor FA-vec kernel

* cont : print metal library load time

* minor : warn to debug + bettern kernel names

ggml-ci

* metal : optimize mul_mv q8_0

ggml-ci

* metal : simplify FA pipeline creation functions

ggml-ci

* metal : improve naming consistency

* metal : safer function constants offsets

ggml-ci

* metal : comments

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-09-08 13:34:56 +03:00
committed by GitHub
parent 9fcb29f22f
commit f28d4f4ac9
4 changed files with 1415 additions and 1325 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -6501,8 +6501,8 @@ 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, 128, 192, 256, 576 }) {
for (int hsv : { 40, 64, 80, 128, 192, 256, 512 }) {
for (int hsk : { 40, 64, 80, 96, 128, 192, 256, 576 }) {
for (int hsv : { 40, 64, 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