ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Load all MoE experts during warmup (#11571)

Browse source 
* llama : introduce llama_set_warmup() API call that controls warmup mode; use all MoE experts during warmup

* common : use new API to enable warmup mode during model warmup

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
This commit is contained in:
fairydreaming 2025-03-14 13:47:05 +01:00 • committed by GitHub
parent add2a3aa5a
commit 8fcb563613
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 22 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

3
common/common.cpp
View file

@ -1033,6 +1033,8 @@ struct common_init_result common_init_from_params(common_params & params) {
if (params.warmup) {
LOG_WRN("%s: warming up the model with an empty run - please wait ... (--no-warmup to disable)\n", __func__);
llama_set_warmup(lctx, true);
std::vector<llama_token> tmp;
llama_token bos = llama_vocab_bos(vocab);
llama_token eos = llama_vocab_eos(vocab);
@ -1063,6 +1065,7 @@ struct common_init_result common_init_from_params(common_params & params) {
llama_kv_self_clear(lctx);
llama_synchronize(lctx);
llama_perf_context_reset(lctx);
llama_set_warmup(lctx, false);
}
iparams.model.reset(model);