mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

common : do not pass prompt tokens to reasoning budget sampler (#22488)

Browse Source
This commit is contained in:
Aldehir Rojas
2026-04-29 14:10:58 -05:00
committed by GitHub
parent 41a63be28e
commit d77599234e
4 changed files with 40 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/sampling.h
+2 -2
View File
@@ -41,8 +41,8 @@ struct common_sampler * common_sampler_init(const struct llama_model * model, st
void common_sampler_free(struct common_sampler * gsmpl);
// if accept_grammar is true, the token is accepted both by the sampling chain and the grammar
void common_sampler_accept(struct common_sampler * gsmpl, llama_token token, bool accept_grammar);
// if is_generated is true, the token is accepted by the sampling chain, the reasoning budget sampler, and the grammar sampler
void common_sampler_accept(struct common_sampler * gsmpl, llama_token token, bool is_generated);
void common_sampler_reset (struct common_sampler * gsmpl);
struct common_sampler * common_sampler_clone (struct common_sampler * gsmpl);