furyhawk/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-21 10:15:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fix broken CPU concat implementation for quantized types (#25247)

Browse Source 
* ggml : fix broken CPU concat implementation for quantized types

* tests : concat tests for quantized types

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
This commit is contained in:
fairydreaming
2026-07-04 13:37:37 +02:00
committed by GitHub
co-authored by Stanisław Szymczyk
parent 2d973636e2
commit ef2d770117
2 changed files with 21 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-backend-ops.cpp
+6
View File
@@ -8918,6 +8918,12 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
}
}
for (ggml_type type_a : { GGML_TYPE_Q4_0, GGML_TYPE_Q4_1, GGML_TYPE_Q5_0, GGML_TYPE_Q5_1, GGML_TYPE_Q8_0 }) {
for (int dim : { 0, 1, 2, 3, }) {
test_cases.emplace_back(new test_concat(type_a, {128, 12, 13, 14}, dim == 0 ? 256 : 7, dim, 0));
}
}
for (ggml_sort_order order : {GGML_SORT_ORDER_ASC, GGML_SORT_ORDER_DESC}) {
for (uint32_t i = 4; i <= 1024*1024; i *= 2) {
test_cases.emplace_back(new test_argsort(GGML_TYPE_F32, {i-1, 1, 1, 1}));