ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-05 22:10:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Allow quantization of ffn_gate_inp (#896)

Browse Source 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-11-05 10:44:32 +02:00
committed by GitHub
parent 15159a87d4
commit abb966eba1
4 changed files with 19 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/llama.cpp
View File

@@ -3863,6 +3863,7 @@ struct llama_model_quantize_params llama_model_quantize_default_params() {
/*.ffn_gate_type =*/ GGML_TYPE_COUNT,
/*.ffn_down_type =*/ GGML_TYPE_COUNT,
/*.ffn_up_type =*/ GGML_TYPE_COUNT,
/*.ffn_gat_inp_type =*/ GGML_TYPE_COUNT,
/*.allow_requantize =*/ false,
/*.quantize_output_tensor =*/ true,
/*.only_copy =*/ false,