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

llama : cleanup unused mmq flags (#5772)

Browse source 
* cleanup unused --no-mul-mat-q,-nommq, -mmq, --mul-mat-q, mul_mat_q

* remove: mul_mat_q in compare llama bench and usage

* update llama-bench

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Pierrick Hymbert 2024-03-01 12:39:06 +01:00 • committed by GitHub
parent 9600d59e01
commit 3ab8b3a92e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 10 additions and 56 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama.cpp
View file

@ -1645,7 +1645,6 @@ struct llama_cparams {
float yarn_beta_slow;
float defrag_thold;
bool mul_mat_q;
bool offload_kqv;
bool do_pooling;
@ -11633,7 +11632,6 @@ struct llama_context_params llama_context_default_params() {
/*.cb_eval_user_data =*/ nullptr,
/*.type_k =*/ GGML_TYPE_F16,
/*.type_v =*/ GGML_TYPE_F16,
/*.mul_mat_q =*/ true,
/*.logits_all =*/ false,
/*.embedding =*/ false,
/*.offload_kqv =*/ true,
@ -11785,7 +11783,6 @@ struct llama_context * llama_new_context_with_model(
cparams.yarn_beta_fast = params.yarn_beta_fast;
cparams.yarn_beta_slow = params.yarn_beta_slow;
cparams.defrag_thold = params.defrag_thold;
cparams.mul_mat_q = params.mul_mat_q;
cparams.offload_kqv = params.offload_kqv;
cparams.do_pooling = params.do_pooling;