Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

common : add support for multiple end sequences in the reasoning budget sampler (#25544)

Browse Source 
* common : extract trie/ac to a separate file

* common : support multiple token sequences in the reasoning budget sampler

* common/trie : return matched word index

* common/trie : rename "word" to "pattern"

* common/reasoning-budget : expose matched end sequence

* common/sampling : replay end sequence when reasoning budget is done

* cont : update to use multiple end sequences

* cont : clean up
This commit is contained in:
Aldehir Rojas
2026-07-25 11:58:09 +02:00
committed by GitHub
parent d67c0b4107
commit 910196f6b3
14 changed files with 497 additions and 254 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/sampling.cpp
+12 -1
View File
@@ -299,7 +299,7 @@ struct common_sampler * common_sampler_init(const struct llama_model * model, st
if (!params.reasoning_budget_start.empty() && !params.reasoning_budget_end.empty() && (params.grammar_lazy || params.reasoning_budget_tokens >= 0 || params.reasoning_control)) {
rbudget = common_reasoning_budget_init(
vocab,
params.reasoning_budget_start,
{params.reasoning_budget_start},
params.reasoning_budget_end,
params.reasoning_budget_forced,
params.reasoning_budget_tokens < 0 ? INT_MAX : params.reasoning_budget_tokens);
@@ -453,6 +453,17 @@ void common_sampler_accept(struct common_sampler * gsmpl, llama_token token, boo
if (gsmpl->rbudget && is_generated) {
llama_sampler_accept(gsmpl->rbudget, token);
// if done, replay end sequence which may contain a grammar trigger
const bool is_done = common_reasoning_budget_get_state(gsmpl->rbudget) == REASONING_BUDGET_DONE;
if (gsmpl->grmr && !accept_grammar && is_done) {
const llama_tokens * end_seq = common_reasoning_budget_get_end_match(gsmpl->rbudget);
if (end_seq) {
for (const llama_token end_token : *end_seq) {
llama_sampler_accept(gsmpl->grmr, end_token);
}
}
}
}
if (gsmpl->grmr && accept_grammar) {