tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-13 11:57:43 -04:00
Code Issues Packages Projects Releases Wiki Activity

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
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);
}