Files
llama.cpp/common/speculative.h
T
Georgi Gerganov 14e733e36f spec : refactor params (#22397)
* spec : refactor params

* cont : fix

* cont : rename "sparam" to "sampling"

* cont : add spec params category

* cont : add info about removed arguments

* cont : skip param length check for spec params

* cont : adapt server tests
2026-04-28 09:07:33 +03:00

47 lines
1.7 KiB
C++

#pragma once
#include "llama.h"
#include "common.h"
struct common_speculative;
// comma separated list of all types
std::string common_speculative_type_name_str();
// convert string to type
enum common_speculative_type common_speculative_type_from_name(const std::string & name);
// convert type to string
std::string common_speculative_type_to_str(enum common_speculative_type type);
common_speculative * common_speculative_init(
common_params_speculative & params,
llama_context * ctx_tgt);
void common_speculative_free(common_speculative * spec);
// optionally call once at the beginning of a new generation
void common_speculative_begin(common_speculative * spec, const llama_tokens & prompt);
// sample up to n_draft tokens and add them to the batch using the draft model
llama_tokens common_speculative_draft(
common_speculative * spec,
const common_params_speculative & params,
const llama_tokens & prompt,
llama_token id_last);
// informs the speculative decoder that n_accepted tokens were accepted by the target model
void common_speculative_accept(common_speculative * spec, uint16_t n_accepted);
int32_t common_speculative_n_max(const common_speculative * spec, const common_params_speculative & params);
int32_t common_speculative_n_min(const common_speculative * spec, const common_params_speculative & params);
// print statistics about the speculative decoding
void common_speculative_print_stats(const common_speculative * spec);
struct common_speculative_deleter {
void operator()(common_speculative * s) { common_speculative_free(s); }
};
typedef std::unique_ptr<common_speculative, common_speculative_deleter> common_speculative_ptr;