mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 29 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
examples/lookup/lookup.cpp
+6 -6
View File
@@ -51,18 +51,18 @@ int main(int argc, char ** argv){
const int64_t t_start_draft_us = ggml_time_us();
common_ngram_cache_update(ngram_cache_context, LLAMA_NGRAM_MIN, LLAMA_NGRAM_MAX, inp, inp.size(), false);
if (!params.lookup_cache_static.empty()) {
if (!params.speculative.lookup_cache_static.empty()) {
try {
ngram_cache_static = common_ngram_cache_load(params.lookup_cache_static);
ngram_cache_static = common_ngram_cache_load(params.speculative.lookup_cache_static);
} catch (std::ifstream::failure const &) {
LOG_ERR("failed to open static lookup cache: %s", params.lookup_cache_static.c_str());
LOG_ERR("failed to open static lookup cache: %s", params.speculative.lookup_cache_static.c_str());
exit(1);
}
}
if (!params.lookup_cache_dynamic.empty()) {
if (!params.speculative.lookup_cache_dynamic.empty()) {
try {
ngram_cache_dynamic = common_ngram_cache_load(params.lookup_cache_dynamic);
ngram_cache_dynamic = common_ngram_cache_load(params.speculative.lookup_cache_dynamic);
} catch (std::ifstream::failure const &) {} // if the file does not exist it will simply be created at the end of the program
}
@@ -210,7 +210,7 @@ int main(int argc, char ** argv){
// Update dynamic ngram cache with context ngram cache and save it to disk:
common_ngram_cache_merge(ngram_cache_dynamic, ngram_cache_context);
common_ngram_cache_save(ngram_cache_dynamic, params.lookup_cache_dynamic);
common_ngram_cache_save(ngram_cache_dynamic, params.speculative.lookup_cache_dynamic);
LOG("\n\n");