COMMITS
/ common/speculative.cpp February 9, 2026
S
spec : remove check rate (#19377)
Sascha Rogmann committed
February 6, 2026
G
common : add common_speculative_is_compat() (#19270)
Georgi Gerganov committed
February 4, 2026
G
spec : fix the check-rate logic of ngram-simple (#19261)
Georgi Gerganov committed
February 3, 2026
G
spec : simplify time measurement using common_time_meas (#19262)
Georgi Gerganov committed
February 2, 2026
S
spec : various improvements ton ngram-map + docs (#19253)
Sascha Rogmann committed
January 30, 2026
G
spec : add ngram-mod (#19164)
Georgi Gerganov committed
January 28, 2026
S
spec : add self‑speculative decoding (no draft model required) + refactor (#18471)
Sascha Rogmann committed
December 17, 2025
G
common : restore grammar-based rejection sampling (#18137)
Georgi Gerganov committed
December 14, 2025
G
common : refactor common_sampler + grammar logic changes (#17937)
Georgi Gerganov committed
August 31, 2025
G
sampling : optimize samplers by reusing bucket sort (#15665)
Georgi Gerganov committed
July 31, 2025
G
server : implement universal assisted decoding (#12635)
g2mt committed
June 6, 2025
G
llama : deprecate llama_kv_self_ API (#14030)
Georgi Gerganov committed
March 13, 2025
G
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
Georgi Gerganov committed
March 4, 2025
M
ggml : portability fixes for VS 2017 (#12150)
mgroeber9110 committed
February 19, 2025
G
speculative : update default params (#11954)
Georgi Gerganov committed
January 12, 2025
G
llama : add `llama_vocab`, functions -> methods, naming (#11110)
Georgi Gerganov committed
December 7, 2024
G
server : fix free of spec context and batch (#10651)
Georgi Gerganov committed
November 25, 2024
G
server : add more information about error (#10455)
Georgi Gerganov committed
G
speculative : refactor and add a simpler example (#10362)
Georgi Gerganov committed