sleepy/llama.cpp
1
0
Fork 0
Code Issues 8 Pull Requests Actions 168 Packages Projects Releases Wiki Activity

common : restore grammar-based rejection sampling (#18137)

Browse Source 
* common : restart grammar-based rejection sampling

* sampling : allow null samplers
This commit is contained in:
Georgi Gerganov
2025-12-17 19:46:00 +02:00
committed by GitHub
parent a2c199e479
commit 4301e27319
5 changed files with 76 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/sampling.h
+6 -3
View File
@@ -57,7 +57,10 @@ struct llama_sampler * common_sampler_get(const struct common_sampler * gsmpl);
// - check if the token fits the grammar (if any)
// - if not: resample by first applying the grammar constraints and then sampling again (slower path)
//
llama_token common_sampler_sample(struct common_sampler * gsmpl, struct llama_context * ctx, int idx);
// if grammar_first is true, the grammar is applied before the samplers (slower)
// useful in cases where all the resulting candidates (not just the sampled one) must fit the grammar
//
llama_token common_sampler_sample(struct common_sampler * gsmpl, struct llama_context * ctx, int idx, bool grammar_first = false);
// generalized version of common_sampler_sample
//
@@ -75,10 +78,10 @@ llama_token common_sampler_sample(struct common_sampler * gsmpl, struct llama_co
//
// returns at least 1 token, up to idxs.size()
//
std::vector<llama_token> common_sampler_sample_and_accept_n(struct common_sampler * gsmpl, struct llama_context * ctx, const std::vector<int> & idxs, const llama_tokens & draft);
std::vector<llama_token> common_sampler_sample_and_accept_n(struct common_sampler * gsmpl, struct llama_context * ctx, const std::vector<int> & idxs, const llama_tokens & draft, bool grammar_first = false);
// assume idxs == [ 0, 1, 2, ..., draft.size() ]
std::vector<llama_token> common_sampler_sample_and_accept_n(struct common_sampler * gsmpl, struct llama_context * ctx, const llama_tokens & draft);
std::vector<llama_token> common_sampler_sample_and_accept_n(struct common_sampler * gsmpl, struct llama_context * ctx, const llama_tokens & draft, bool grammar_first = false);
uint32_t common_sampler_get_seed(const struct common_sampler * gsmpl);