ollama/llama/llama-sampling.h

/**
 * llama.cpp - commit ba1cb19cdd0d92e012e0f6e009e0620f854b6afd - do not edit this file
 *
 * MIT License
 *
 * Copyright (c) 2023-2024 The ggml authors
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in all
 * copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#pragma once

// TODO: rename llama-sampling.h/.cpp to llama-sampler.h/.cpp ?

#include "llama-grammar.h"

struct llama_vocab;
struct llama_grammar;

// sampler chain

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;
};

struct llama_sampler * llama_sampler_init_grammar_impl(
        const struct llama_vocab & vocab,
                      const char * grammar_str,
                      const char * grammar_root);

struct llama_sampler * llama_sampler_init_infill_impl(
        const struct llama_vocab & vocab);

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);