Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 14:20:31 +01:00
Code Issues Packages Projects Releases Wiki Activity

ggml : update ggml_backend_cpu_device_supports_op (#10867)

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

ggml-ci

* ggml : disable tests involving i-matrix quantization

* ggml : update ggml_backend_cpu_device_supports_op

ggml-ci
This commit is contained in:
Georgi Gerganov 2024-12-17 18:35:42 +02:00 committed by GitHub
parent 05c3a444b8
commit 0006f5a74a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-cpu/ggml-cpu.cpp
View File

@ -394,8 +394,11 @@ static bool ggml_backend_cpu_device_supports_op(ggml_backend_dev_t dev, const st
switch (op->op) {
case GGML_OP_CPY:
return
op->type != GGML_TYPE_IQ3_XXS &&
op->type != GGML_TYPE_IQ3_S &&
op->type != GGML_TYPE_IQ2_XXS &&
op->type != GGML_TYPE_IQ2_XS &&
op->type != GGML_TYPE_IQ2_S &&
op->type != GGML_TYPE_IQ1_S &&
op->type != GGML_TYPE_IQ1_M; // missing type_traits.from_float
case GGML_OP_MUL_MAT:

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

@ -3549,8 +3549,8 @@ 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
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}) {