happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

llama-quant : default ftype param `Q5_1` --> `Q8_0` 

Change the default `ftype` in `llama_model_quantize_params` from
`LLAMA_FTYPE_MOSTLY_Q5_1` to `LLAMA_FTYPE_MOSTLY_Q8_0`.

In case some external program naively uses the default quantization
params, we should probably default to a known-good type like Q8_0 rather
than Q5_1, which is rather old.
This commit is contained in:
ddh0 2026-03-20 18:26:46 -05:00
parent b1c70e2e54
commit 228d573424
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-quant.cpp
View File

@ -1271,7 +1271,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
llama_model_quantize_params llama_model_quantize_default_params() {
llama_model_quantize_params result = {
/*.nthread =*/ 0,
/*.ftype =*/ LLAMA_FTYPE_MOSTLY_Q5_1,
/*.ftype =*/ LLAMA_FTYPE_MOSTLY_Q8_0,
/*.output_tensor_type =*/ GGML_TYPE_COUNT,
/*.token_embedding_type =*/ GGML_TYPE_COUNT,
/*.allow_requantize =*/ false,