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 : move random seed generation to the samplers (#9398)

Browse Source 
* llama_sampler_penalties : clamp penalty_last_n to zero
This commit is contained in:
slaren
2024-09-10 18:04:25 +02:00
committed by GitHub
parent 00ba2ff781
commit 49006c67b4
10 changed files with 92 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/sampling.h
View File

@ -60,6 +60,8 @@ void gpt_perf_print(const struct llama_context * ctx, const struct gpt_sampler *
//
llama_token gpt_sampler_sample(struct gpt_sampler * gsmpl, struct llama_context * ctx, int idx, bool grammar_first = false);
uint32_t gpt_sampler_get_seed(const struct gpt_sampler * gsmpl);
// helpers
// access the internal list of current candidate tokens