Files
llama.cpp/src/llama-sampling.h
T

49 lines
1.5 KiB
C++
Raw Normal View History

#pragma once
2024-09-07 15:16:19 +03:00
// TODO: rename llama-sampling.h/.cpp to llama-sampler.h/.cpp ?
2024-09-07 15:16:19 +03:00
#include "llama-grammar.h"
2024-09-07 15:16:19 +03:00
struct llama_vocab;
struct llama_grammar;
2024-09-07 15:16:19 +03:00
// sampler chain
2024-09-07 15:16:19 +03:00
struct llama_sampler_chain {
llama_sampler_chain_params params;
std::vector<struct llama_sampler *> samplers;
// timing
mutable int64_t t_sample_us;
mutable int32_t n_sample;
};
2024-09-07 15:16:19 +03:00
struct llama_sampler * llama_sampler_init_grammar_impl(
const struct llama_vocab & vocab,
const char * grammar_str,
const char * grammar_root);
2024-10-15 16:35:33 +03:00
struct llama_sampler * llama_sampler_init_infill_impl(
const struct llama_vocab & vocab);
2024-10-25 10:07:34 -06:00
struct llama_sampler * llama_sampler_init_dry_impl(
const struct llama_vocab & vocab,
int32_t context_size,
float dry_multiplier,
float dry_base,
int32_t dry_allowed_length,
int32_t dry_penalty_last_n,
const char ** seq_breakers,
size_t num_breakers);
struct llama_sampler * llama_sampler_init_dry_testing(
int32_t context_size,
float dry_multiplier,
float dry_base,
int32_t dry_allowed_length,
int32_t dry_penalty_last_n,
const std::vector<std::vector<llama_token>>& seq_breakers);