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

2
common/common.cpp
View file

@ -1281,7 +1281,6 @@ struct llama_context_params llama_context_params_from_gpt_params(const gpt_param
cparams.n_batch = params.n_batch;
cparams.n_threads = params.n_threads;
cparams.n_threads_batch = params.n_threads_batch == -1 ? params.n_threads : params.n_threads_batch;
cparams.mul_mat_q = params.mul_mat_q;
cparams.seed = params.seed;
cparams.logits_all = params.logits_all;
cparams.embedding = params.embedding;
@ -1725,7 +1724,6 @@ void dump_non_result_info_yaml(FILE * stream, const gpt_params & params, const l
fprintf(stream, "n_predict: %d # default: -1 (unlimited)\n", params.n_predict);
fprintf(stream, "n_probs: %d # only used by server binary, default: 0\n", sparams.n_probs);
fprintf(stream, "no_mmap: %s # default: false\n", !params.use_mmap ? "true" : "false");
fprintf(stream, "no_mul_mat_q: %s # default: false\n", !params.mul_mat_q ? "true" : "false");
fprintf(stream, "no_penalize_nl: %s # default: false\n", !sparams.penalize_nl ? "true" : "false");
fprintf(stream, "ppl_output_type: %d # default: 0\n", params.ppl_output_type);
fprintf(stream, "ppl_stride: %d # default: 0\n", params.ppl_stride);