ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-30 03:11:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

add dry sampler (#513)

Browse Source 
* add dry sampler

* use vocab instead of model in dry_init function

* fix compile error for build test

---------

Co-authored-by: firecoperana <firecoperana>
This commit is contained in:
firecoperana
2025-06-19 02:24:53 -05:00
committed by GitHub
parent 638fb80e8a
commit d1f92e24d3
21 changed files with 743 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/lookahead/lookahead.cpp
View File

@@ -118,7 +118,7 @@ int main(int argc, char ** argv) {
llama_batch batch = llama_batch_init(params.n_ctx, 0, W + G + 1);
// target model sampling context
struct llama_sampling_context * ctx_sampling = llama_sampling_init(params.sparams);
struct llama_sampling_context * ctx_sampling = llama_sampling_init(llama_get_model_vocab(model), params.sparams);
// verification n-grams
std::vector<ngram_data> ngrams_cur(G);