thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

common/parser: add proper reasoning tag prefill reading (#20424)

Browse source 
* Implement proper prefill extraction

* Refactor cli parameters, update docs, move reasoning budget sampler part to common/reasoning-budget.cpp

* Update tools/server/server-task.cpp

* refactor: move grammars to variant, remove grammar_external, handle exception internally

* Make code less C++y

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Piotr Wilkin (ilintar) 2026-03-19 16:58:21 +01:00 • committed by GitHub
parent c1258830b2
commit 5e54d51b19
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
33 changed files with 651 additions and 454 deletions
Download patch file Download diff file Expand all files Collapse all files

26
common/reasoning-budget.h
View file

@ -24,14 +24,26 @@ enum common_reasoning_budget_state {
// 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
// forced_tokens - token sequence forced when budget expires
// budget - max tokens allowed in the reasoning block
// initial_state - initial state of the sampler (e.g. IDLE or COUNTING)
// note: COUNTING with budget <= 0 is promoted to FORCING
// 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
// forced_tokens - token sequence forced when budget expires
// budget - max tokens allowed in the reasoning block
// prefill_tokens - tokens already present in the prompt (generation prompt);
// used to determine the initial state: COUNTING if they begin
// with start_tokens (but don't also end with end_tokens),
// IDLE otherwise. COUNTING with budget <= 0 is promoted to FORCING.
//
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,
const std::vector<llama_token> & prefill_tokens = {});
// Variant that takes an explicit initial state (used by tests and clone).
// COUNTING with budget <= 0 is promoted to FORCING.
struct llama_sampler * common_reasoning_budget_init(
const struct llama_vocab * vocab,
const std::vector<llama_token> & start_tokens,