mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-02-23 22:54:10 +00:00
09a88c9ae5
* wip: port MTP architecture Ports the Multi-Token Prediction (MTP) architecture to the older `llama.cpp` codebase used by `ikllama`. Changes include: - Updating `llama_batch` to support `mtp_params`. - Modifying `llama_decode_internal` (and `encode`) to handle MTP operations (Warmup, Update, Draft). - Adding public APIs for MTP state management (`llama_set_draft_input_hidden_state`). - Adapting the embedding extraction logic to skip MTP update passes. * Refactors `server_slot` to support generic speculative decoding (MTP or Draft Model). * core: enable hybrid outputs (logits + embeddings) for MTP support * fix(mtp): correct KV-cache slot finding for updates * fix(mtp): persist hidden states to prevent context corruption during drafting * refactor(mtp): clean unused code * fix(mtp): update server to new functions name * fix(mtp): fix graph and save hidden state * mtp: refactor integration, context params and kv cache search * mtp: fix hidden state extraction and speculative acceptance flow * server: fix MTP warmup for long prompts and reset token buffer * llama: refactor MTP operation state to context parameters * server: fix n_past calculation in MTP acceptance * llama: fix mtp enable flags * speculative: refactor MTP to use common_speculative interface * context: remove unused signatures * clip: fix deprecated enum-enum conversion warning * common: fix format string crash in help message * context: fix mtp activation logic
61 lines
2.0 KiB
C++
61 lines
2.0 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);
|
|
|
|
// check if the llama_context is compatible for speculative decoding
|
|
// note: clears the memory of the context
|
|
bool common_speculative_is_compat(llama_context * ctx_tgt);
|
|
|
|
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);
|
|
|
|
// print statistics about the speculative decoding
|
|
void common_speculative_print_stats(const common_speculative * spec);
|
|
|
|
// Generates speculative draft tokens using the Multi-Token Prediction (MTP) architecture.
|
|
std::vector<llama_token> mtp_speculative_gen_draft(
|
|
struct common_sampler * smpl,
|
|
struct llama_context * ctx,
|
|
int n_draft,
|
|
float p_min,
|
|
llama_token id_last,
|
|
int32_t n_past,
|
|
llama_seq_id seq_id);
|
|
|
|
void mtp_update_kv_cache(struct llama_context * ctx, const llama_batch& batch, bool is_prompt_warmup);
|
|
|
|
void mtp_accept_tokens(
|
|
struct llama_context * ctx,
|
|
const std::vector<llama_token> & ids,
|
|
int32_t n_past_base,
|
|
llama_seq_id seq_id
|
|
);
|