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

speculative : add grammar support (#2991)

Browse source 
* speculative : add grammar support

* grammars : add json_arr.gbnf

* grammar : add comments to new grammar file

* grammar : remove one nested level

* common : warm-up with 2 tokens - seems to work better

* speculative : print draft token pieces

* speculative : reuse grammar parser + better logs and comments

* speculative : avoid grammar_mem

* make : fix speculative build
This commit is contained in:
Georgi Gerganov 2023-09-05 08:46:17 +03:00 • committed by GitHub
parent 2ba85c8609
commit 921772104b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 126 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.cpp
View file

@ -772,7 +772,7 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
{
LOG("warming up the model with an empty run\n");
const std::vector<llama_token> tmp = { llama_token_bos(lctx), };
const std::vector<llama_token> tmp = { llama_token_bos(lctx), llama_token_eos(lctx), };
llama_eval(lctx, tmp.data(), tmp.size(), 0, params.n_threads);
llama_reset_timings(lctx);
}