tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 04:15:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix empty ring buffer push (#9358)

Browse Source
This commit is contained in:
Georgi Gerganov
2024-09-08 00:33:33 +03:00
committed by GitHub
parent faf69d4237
commit f12295b8a9
2 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/sampling.cpp
View File

@ -145,7 +145,7 @@ struct gpt_sampler * gpt_sampler_init(const struct llama_model * model, const st
/* .params = */ params,
/* .grmr = */ llama_sampler_init_grammar(model, params.grammar.c_str(), "root"),
/* .chain = */ llama_sampler_chain_init(lparams),
/* .prev = */ ring_buffer<llama_token>(params.n_prev),
/* .prev = */ ring_buffer<llama_token>(std::max(32, params.n_prev)),
/* .cur = */ {},
/* .cur_p = */ {},
};