 Cebtenzzre
|
80291a1d02
common : do not use GNU zero-length __VA_ARGS__ extension (#3195)
|
il y a 2 ans |
 Roland
|
2d770505a8
llama : remove mtest (#3177)
|
il y a 2 ans |
 FK
|
84e723653c
speculative: add --n-gpu-layers-draft option (#3063)
|
il y a 2 ans |
|
Cebtenzzre
|
00d62adb79
fix some warnings from gcc and clang-tidy (#3038)
|
il y a 2 ans |
 Georgi Gerganov
|
e36ecdccc8
build : on Mac OS enable Metal by default (#2901)
|
il y a 2 ans |
|
Georgi Gerganov
|
47068e5170
speculative : PoC for speeding-up inference via speculative sampling (#2926)
|
il y a 2 ans |
 staviq
|
8341a25957
main : log file (#2748)
|
il y a 2 ans |
 Johannes Gäßler
|
6b73ef1201
YAML result logging + preset script (#2657)
|
il y a 2 ans |
|
Georgi Gerganov
|
edd4c14817
llama : more tokenizer fixes (#2810)
|
il y a 2 ans |
 Matt Pulver
|
c82742ac9c
llama : add llama_beam_search() (#2267)
|
il y a 2 ans |
|
Georgi Gerganov
|
cf658adc83
llm : add Falcon support (#2717)
|
il y a 2 ans |
 Kawrakow
|
62959e740e
Strided perplexity (#2714)
|
il y a 2 ans |
|
Johannes Gäßler
|
c63bb1d16a
CUDA: use mul_mat_q kernels by default (#2683)
|
il y a 2 ans |
|
Georgi Gerganov
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
il y a 2 ans |
