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

spec : add self‑speculative decoding (no draft model required) + refactor (#18471)

Browse Source 
* server: introduce self-speculative decoding

* server: moved self-call into speculative.cpp

* can_speculate() includes self-speculation

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* server: can_speculate() tests self-spec

* server: replace can_speculate() with slot.can_speculate()

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* common: use %zu format specifier for size_t in logging

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* server: can_speculate() requires a task instance

* common: ngram map, config self-speculative decoding

* common: add enum common_speculative_type

* common: add vector of speculative states

* common: add option --spec-draftless

* server: cleanup (remove slot.batch_spec, rename)

* common: moved self-spec impl to ngram-map

* common: cleanup (use common_speculative_state_draft)

* spec : refactor

* cont : naming

* spec: remove --spec-config

* doc: (draftless) speculative decoding

* common: print performance in spec decoding

* minor : cleanup

* common : better names

* minor : cleanup + fix build

* minor: comments

* CODEOWNERS: add common/ngram-map.* (#18471)

* common : rename speculative.draftless_type -> speculative.type

* ngram-map : fix uninitialized values

* ngram-map : take into account the input can become shorter

* ngram-map : revert len check for now

* arg : change `--spec-draftless` -> `--spec-type`

* spec : add common_speculative_state::accept()

* spec : refactor + add common_speculative_begin()

* spec : fix begin() call with mtmd

* spec : additional refactor + remove common_speculative_params

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Sascha Rogmann
2026-01-28 18:42:42 +01:00
committed by GitHub
parent ebf5725870
commit 72d3b1898a
19 changed files with 1649 additions and 444 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/ngram-cache.h
+2 -2
View File
@@ -88,12 +88,12 @@ void common_ngram_cache_draft(
// Save an ngram cache to a file.
// ngram_cache: the ngram cache to save.
// filename: the path under which to save the ngram cache.
void common_ngram_cache_save(common_ngram_cache & ngram_cache, std::string & filename);
void common_ngram_cache_save(common_ngram_cache & ngram_cache, const std::string & filename);
// Load an ngram cache saved with common_ngram_cache_save.
// filename: the path from which to load the ngram cache.
// returns: an ngram cache containing the information saved to filename.
common_ngram_cache common_ngram_cache_load(std::string & filename);
common_ngram_cache common_ngram_cache_load(const std::string & filename);
// Merge two ngram caches.
// ngram_cache_target: the ngram cache to which to add the information from ngram_cache_add.