CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: mul_mat_q=true llama_context_params default (#2912)

Browse Source
This commit is contained in:
Johannes Gäßler
2023-08-30 21:46:19 +02:00
committed by GitHub
parent 71d6975559
commit 8afe228000
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
llama.cpp
View File

@@ -5287,7 +5287,7 @@ struct llama_context_params llama_context_default_params() {
/*.progress_callback =*/ nullptr, /*.progress_callback =*/ nullptr,
/*.progress_callback_user_data =*/ nullptr, /*.progress_callback_user_data =*/ nullptr,
/*.low_vram =*/ false, /*.low_vram =*/ false,
/*.mul_mat_q =*/ false, /*.mul_mat_q =*/ true,
/*.f16_kv =*/ true, /*.f16_kv =*/ true,
/*.logits_all =*/ false, /*.logits_all =*/ false,
/*.vocab_only =*/ false, /*.vocab_only =*/ false,