thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

metal : improve MUL_MAT_ID (#15541)

Browse source 
* metal : mul_mm_id remove hdst

* metal : remove mul_mm_id hsrc1

* metal : mul_mm_id simplify + add test

* metal : opt mul_mm_id map0

* metal : optimize mul_mm_id id gathering

* metal : mul/div opt

* metal : optimize mul_mm_id_map0

ggml-ci
This commit is contained in:
Georgi Gerganov 2025-08-26 12:46:15 +03:00 • committed by GitHub
parent c4e9239064
commit 1d8d83deaa
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 180 additions and 228 deletions
Download patch file Download diff file Expand all files Collapse all files

1
tests/test-backend-ops.cpp
View file

@ -6018,6 +6018,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
for (bool b : {false, true}) {
test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_F16, GGML_TYPE_F32, 16, 16, b, 32, 1024, 16));
test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_F16, GGML_TYPE_F32, 2, 2, b, 32, 8192, 64));
test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_F16, GGML_TYPE_F32, 16, 16, b, 50, 200, 64));
}
test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_F16, GGML_TYPE_F32, 1, 1, false, 8, 16, 1));