mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 33 Packages Projects Releases Wiki Activity

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
33 changed files with 651 additions and 454 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/reasoning-budget.cpp
+52 -8
View File
@@ -163,9 +163,15 @@ static void common_reasoning_budget_reset(struct llama_sampler * smpl) {
ctx->force_pos = 0;
}
// forward declaration for use in clone
static struct llama_sampler * common_reasoning_budget_init_state(
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);
static struct llama_sampler * common_reasoning_budget_clone(const struct llama_sampler * smpl) {
const auto * ctx = (const common_reasoning_budget_ctx *) smpl->ctx;
return common_reasoning_budget_init(
return common_reasoning_budget_init_state(
ctx->vocab,
ctx->start_matcher.tokens,
ctx->end_matcher.tokens,
@@ -191,13 +197,13 @@ static struct llama_sampler_i common_reasoning_budget_i = {
/* .backend_set_input = */ nullptr,
};
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) {
static struct llama_sampler * common_reasoning_budget_init_state(
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) {
// promote COUNTING with budget <= 0 to FORCING
if (initial_state == REASONING_BUDGET_COUNTING && budget <= 0) {
initial_state = REASONING_BUDGET_FORCING;
@@ -217,3 +223,41 @@ struct llama_sampler * common_reasoning_budget_init(
}
);
}
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) {
// Determine initial state from prefill: COUNTING if the prefill begins with
// the start sequence but does not also contain the end sequence after it.
common_reasoning_budget_state initial_state = REASONING_BUDGET_IDLE;
if (!prefill_tokens.empty() && !start_tokens.empty() &&
prefill_tokens.size() >= start_tokens.size() &&
std::equal(start_tokens.begin(), start_tokens.end(), prefill_tokens.begin())) {
initial_state = REASONING_BUDGET_COUNTING;
// If the end sequence also follows the start in the prefill, reasoning
// was opened and immediately closed — stay IDLE.
if (!end_tokens.empty() &&
prefill_tokens.size() >= start_tokens.size() + end_tokens.size()) {
auto end_start = prefill_tokens.end() - (ptrdiff_t) end_tokens.size();
if (end_start >= prefill_tokens.begin() + (ptrdiff_t) start_tokens.size() &&
std::equal(end_tokens.begin(), end_tokens.end(), end_start)) {
initial_state = REASONING_BUDGET_IDLE;
}
}
}
return common_reasoning_budget_init_state(vocab, start_tokens, end_tokens, forced_tokens, budget, 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) {
return common_reasoning_budget_init_state(vocab, start_tokens, end_tokens, forced_tokens, budget, initial_state);
}