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

Merge branch 'master' into compilade/refactor-kv-cache

Browse source
This commit is contained in:
Francis Couture-Harpin 2024-07-04 17:33:52 -04:00
commit 9b38f8bf65
102 changed files with 4745 additions and 1675 deletions
Download patch file Download diff file Expand all files Collapse all files

21
common/common.cpp
View file

@ -757,7 +757,7 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
params.cache_type_v = argv[++i];
return true;
}
if (arg == "--multiline-input") {
if (arg == "-mli" || arg == "--multiline-input") {
params.multiline_input = true;
return true;
}
@ -2070,7 +2070,24 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
if (params.warmup) {
LOG("warming up the model with an empty run\n");
std::vector<llama_token> tmp = { llama_token_bos(model), llama_token_eos(model), };
std::vector<llama_token> tmp;
llama_token bos = llama_token_bos(model);
llama_token eos = llama_token_eos(model);
// some models (e.g. T5) don't have a BOS token
if (bos != -1) {
tmp.push_back(bos);
}
tmp.push_back(eos);
if (llama_model_has_encoder(model)) {
llama_encode(lctx, llama_batch_get_one(tmp.data(), tmp.size(), 0, 0));
llama_token decoder_start_token_id = llama_model_decoder_start_token(model);
if (decoder_start_token_id == -1) {
decoder_start_token_id = bos;
}
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));
llama_past_clear(lctx);
llama_synchronize(lctx);