mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

server : speculative checkpointing (#19493)

Browse Source 
* server : speculative decoding using checkpoints

* server : fix draft check with checkpoints

* server : rename spec vars

* server : log levels

* server : refactored spec logic to speculative.cpp

* server : renamed spec checkpoints option

* server : fix spec checkpoints, logging

* speculative : checkpoints with draft model, logging

* server : n_tokens_cur and create_checkpoint in draft

* server : fix server_speculative_callback (slot.id)

* spec : fix ngram-map/begin idx_last_check

* spec : init ckpt (begin() wasn't called)

* chore: update webui build output

* server : restore sampler in spec checkpoint and clear mem

* cont : avoid --spec-use-checkpoints argument

* cont : remove server_prompt_checkpoint_with_size

* spec : rename (leave_draft_state)

* cont : clean-up

* cont : do not ignore partial drafts even if the are short

* cont : spec callback owned by session

* cont : simplify

* cont : avoid empty speculative session

* cont : simplify

* cont : simplify

* cont : enable mtmd speculative decoding

* cont : keep the spec sampler alive

* cont : simplify

* cont : fix nullptr deref + draft checkpoints

* cont : remove common_speculative_accept_response

* cont : remove callback

* cont : simplify

* cont : minor

* cont : simplify

* cont : fix accepted number

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Sascha Rogmann
2026-04-19 09:24:06 +02:00
committed by GitHub
parent 91fef95362
commit 455d8e4be8
10 changed files with 421 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.h
+2 -2
View File
@@ -11,7 +11,6 @@
#include <sstream>
#include <string>
#include <string_view>
#include <variant>
#include <vector>
#include <map>
@@ -303,7 +302,7 @@ struct common_params_speculative {
// general-purpose speculative decoding parameters
int32_t n_max = 16; // maximum number of tokens to draft during speculative decoding
int32_t n_min = 0; // minimum number of draft tokens to use for speculative decoding
int32_t n_min = 0; // minimum number of draft tokens to use for speculative decoding
float p_split = 0.1f; // speculative decoding split probability
float p_min = 0.75f; // minimum speculative decoding probability (greedy)
@@ -312,6 +311,7 @@ struct common_params_speculative {
uint16_t ngram_size_n = 12; // ngram size for lookup
uint16_t ngram_size_m = 48; // mgram size for speculative tokens
uint16_t ngram_min_hits = 1; // minimum hits at ngram/mgram lookup for mgram to be proposed
bool use_checkpoints = false; // use checkpoints to rewind in token history of recurrent models
std::shared_ptr<common_ngram_mod> ngram_mod;