vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	examples/run/run.cpp
#	ggml/src/ggml-cann/aclnn_ops.cpp
This commit is contained in:
Concedo 2025-03-15 19:54:19 +08:00
commit 67851e5415
9 changed files with 39 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

3
common/common.cpp
View file

@ -1037,6 +1037,8 @@ 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);
@ -1067,6 +1069,7 @@ 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);