vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : fix cpy op for IQ-quants to use reference impl

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-12-17 17:54:04 +02:00
parent 382bc7f2e8
commit b0597b1493
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
2 changed files with 16 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

7
tests/test-backend-ops.cpp
View file

@ -3549,8 +3549,11 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
for (ggml_type type_src : {GGML_TYPE_F16, GGML_TYPE_F32}) {
for (ggml_type type_dst : all_types) {
test_cases.emplace_back(new test_cpy(type_src, type_dst, {256, 4, 4, 4}));
test_cases.emplace_back(new test_cpy(type_src, type_dst, {256, 2, 3, 4}, {0, 2, 1, 3})); // cpy by rows
//if (type_dst == GGML_TYPE_IQ2_S || type_dst == GGML_TYPE_IQ3_XXS || type_dst == GGML_TYPE_IQ3_S) {
// continue;
//}
test_cases.emplace_back(new test_cpy(type_src, type_dst, {256, 4, 4, 4}));
test_cases.emplace_back(new test_cpy(type_src, type_dst, {256, 2, 3, 4}, {0, 2, 1, 3})); // cpy by rows
}
}
for (ggml_type type_src : {GGML_TYPE_F16, GGML_TYPE_F32}) {