mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-29 07:34:18 +01:00
d9d54e498d
* speculative : refactor and add a simpler example ggml-ci * speculative : clean-up and add comments and TODOs [no ci] * speculative : manage context in common_speculative ggml-ci * speculative : simplify ggml-ci * speculative : simplify (cont) ggml-ci * speculative : add --draft-min CLI arg * speculative : minor fixup * make : build fixes * speculative : do not redraft previous drafts ggml-ci * speculative : fix the draft sampling ggml-ci * speculative : fix compile warning * common : refactor args ggml-ci * common : change defaults [no ci] * common : final touches ggml-ci
29 lines
883 B
C
29 lines
883 B
C
#pragma once
|
|
|
|
#include "llama.h"
|
|
#include "common.h"
|
|
|
|
struct common_speculative;
|
|
|
|
struct common_speculative_params {
|
|
int n_draft = 16; // max drafted tokens
|
|
int n_reuse = 256;
|
|
|
|
float p_min = 0.9f; // min probabiliy required to accept a token in the draft
|
|
};
|
|
|
|
struct common_speculative * common_speculative_init(struct llama_context * ctx_dft);
|
|
|
|
void common_speculative_free(struct common_speculative * spec);
|
|
|
|
bool common_speculative_are_compatible(
|
|
const struct llama_context * ctx_tgt,
|
|
const struct llama_context * ctx_dft);
|
|
|
|
// sample up to n_draft tokens and add them to the batch using the draft model
|
|
llama_tokens common_speculative_gen_draft(
|
|
struct common_speculative * spec,
|
|
struct common_speculative_params params,
|
|
const llama_tokens & prompt,
|
|
llama_token id_last);
|