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

common : call llama_decode() during warmup only if the model has decoder

Browse source
This commit is contained in:
Stanisław Szymczyk 2024-08-09 21:58:13 +02:00
parent 94597ecfe2
commit 788b4d199e
1 changed files with 3 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/common.cpp
View file

@ -2156,7 +2156,9 @@ 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);