CUDA: mul_mat_q=true llama_context_params default (#2912)

This commit is contained in:
Johannes Gäßler 2023-08-30 21:46:19 +02:00 committed by GitHub
parent 71d6975559
commit 8afe228000
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

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