index
:
ik_llama.cpp.git
main
Unnamed repository; edit this file 'description' to name the repository.
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
examples
/
speculative
/
speculative.cpp
Age
Commit message (
Expand
)
Author
2024-08-12
Merge mainline - Aug 12 2024 (#17)
Kawrakow
2024-06-04
common : refactor cli arg parsing (#7675)
Georgi Gerganov
2024-04-21
llama : support Llama 3 HF conversion (#6745)
Pedro Cuenca
2024-04-09
BERT tokenizer fixes (#6498)
Jared Van Bortel
2024-03-26
llama : greatly reduce output buffer memory usage (#6122)
compilade
2024-03-24
sampling : deduplicated code for probability distribution access (#6240)
Minsoo Cheong
2024-03-04
fix speculative decoding build on windows (#5874)
Jeffrey Quesnelle
2024-03-04
speculative : implement stochastic speculative sampling (#5625)
Minsoo Cheong
2024-02-16
ggml : add numa options (#5377)
bmwl
2024-01-16
speculative : threading options (#4959)
stduhpf
2023-12-12
english : use `typos` to fix comments and logs (#4354)
Richard Kiss
2023-12-06
speculative : support `--color` (#4343)
stduhpf
2023-11-20
speculative : fix prompt tokenization in speculative example (#4025)
Branden Butler
2023-11-03
speculative : change default p_accept to 0.5 + CLI args (#3919)
Georgi Gerganov
2023-11-02
build : link against build info instead of compiling against it (#3879)
cebtenzzre
2023-10-28
llama : add option for greedy sampling with probs (#3813)
Georgi Gerganov
2023-10-28
speculative : ensure draft and target model vocab matches (#3812)
Kerfuffle
2023-10-23
llama : remove token functions with `context` args in favor of `model` (#3720)
Marcus Dunn
2023-10-20
sampling : refactor init to use llama_sampling_params (#3696)
Georgi Gerganov
2023-10-18
speculative : bug fixes
Georgi Gerganov
2023-10-18
speculative : add tree-based sampling example (#3624)
Georgi Gerganov
2023-10-11
common : fix mirostat state when using multiple sequences (#3543)
Kerfuffle
2023-10-03
llama : fix session saving/loading (#3400)
Georgi Gerganov
2023-09-28
llama.cpp : split llama_context_params into model and context params (#3301)
slaren
2023-09-28
llama : custom attention mask + parallel decoding + no context swaps (#3228)
Georgi Gerganov
2023-09-14
speculative : add heuristic algorithm (#3006)
Leng Yue
2023-09-13
speculative: add --n-gpu-layers-draft option (#3063)
FK
2023-09-08
build : do not use _GNU_SOURCE gratuitously (#2035)
Przemysław Pawełczyk
2023-09-05
speculative : add grammar support (#2991)
Georgi Gerganov
2023-09-03
speculative : PoC for speeding-up inference via speculative sampling (#2926)
Georgi Gerganov