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

Merge branch 'master' into gg/flash-attn

Browse source
This commit is contained in:
Georgi Gerganov 2024-03-27 10:24:09 +02:00
commit 013721df2b
No known key found for this signature in database
GPG key ID: BF970631944C16B7
157 changed files with 19090 additions and 15488 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tests/test-backend-ops.cpp
View file

@ -2040,7 +2040,7 @@ static bool test_backend(ggml_backend_t backend, test_mode mode, const char * op
GGML_TYPE_Q4_K, GGML_TYPE_Q5_K,
GGML_TYPE_Q6_K,
GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S,
GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ1_S,
GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M,
GGML_TYPE_IQ4_NL, GGML_TYPE_IQ3_S, GGML_TYPE_IQ4_XS,
};

5
tests/test-quantize-fns.cpp
View file

@ -138,11 +138,6 @@ int main(int argc, char * argv[]) {
const ggml_type ei = (ggml_type)i;
if (ei == GGML_TYPE_IQ2_XXS || ei == GGML_TYPE_IQ2_XS) {
printf("Skip %s due to missing quantization functionality\n", ggml_type_name(ei));
continue;
}
printf("Testing %s\n", ggml_type_name((ggml_type) i));
ggml_quantize_init(ei);