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/reasoning-budget.h
+16 -10
View File
@@ -2,6 +2,8 @@
#include "llama.h"
#include "common.h"
#include <cstdint>
#include <vector>
@@ -17,30 +19,34 @@ enum common_reasoning_budget_state {
// reasoning block (e.g. between <think> and </think>).
//
// State machine: IDLE -> COUNTING -> WAITING_UTF8 -> FORCING -> DONE
// IDLE: passthrough, watching for start_tokens sequence
// COUNTING: counting down remaining tokens, watching for natural end_tokens
// IDLE: passthrough, watching for a start sequence
// COUNTING: counting down remaining tokens, watching for a natural end sequence
// WAITING_UTF8: budget exhausted, allowing tokens to complete a UTF-8 sequence
// FORCING: forces forced_tokens token-by-token (all other logits -> -inf)
// DONE: passthrough forever
//
// Parameters:
// vocab - vocabulary (used for UTF-8 boundary detection; can be nullptr)
// start_tokens - token sequence that activates counting
// end_tokens - token sequence for natural deactivation
// start_seqs - token sequences, any of which activates counting
// end_seqs - token sequences, any of which naturally deactivates
// forced_tokens - token sequence forced when budget expires
// budget - max tokens allowed in the reasoning block
// initial_state - initial state
//
struct llama_sampler * common_reasoning_budget_init(
const struct llama_vocab * vocab,
const std::vector<llama_token> & start_tokens,
const std::vector<llama_token> & end_tokens,
const std::vector<llama_token> & forced_tokens,
int32_t budget,
common_reasoning_budget_state initial_state = REASONING_BUDGET_IDLE);
const struct llama_vocab * vocab,
const std::vector<llama_tokens> & start_seqs,
const std::vector<llama_tokens> & end_seqs,
const llama_tokens & forced_tokens,
int32_t budget,
common_reasoning_budget_state initial_state = REASONING_BUDGET_IDLE);
common_reasoning_budget_state common_reasoning_budget_get_state(const struct llama_sampler * smpl);
// The end sequence that transitioned the sampler to DONE, or nullptr if none
// was recorded. Cleared when a new start sequence re-arms the sampler.
const llama_tokens * common_reasoning_budget_get_end_match(const struct llama_sampler * smpl);
// Manually transition the reasoning budget sampler into the FORCING state.
// Returns true if the transition occurred.
bool common_reasoning_budget_force(struct llama_sampler * smpl);