vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	src/llama.cpp
This commit is contained in:
Concedo 2024-08-10 22:53:42 +08:00
commit 7fab499b79
8 changed files with 719 additions and 338 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/common.cpp
View file

@ -2157,7 +2157,9 @@ struct llama_init_result llama_init_from_gpt_params(gpt_params & params) {
tmp.clear();
tmp.push_back(decoder_start_token_id);
}
llama_decode(lctx, llama_batch_get_one(tmp.data(), std::min(tmp.size(), (size_t) params.n_batch), 0, 0));
if (llama_model_has_decoder(model)) {
llama_decode(lctx, llama_batch_get_one(tmp.data(), std::min(tmp.size(), (size_t) params.n_batch), 0, 0));
}
llama_kv_cache_clear(lctx);
llama_synchronize(lctx);
llama_reset_timings(lctx);