Cebtenzzre
|
de2fe892af
examples : replace fprintf to stdout with printf (#3017)
|
2 лет назад |
Georgi Gerganov
|
921772104b
speculative : add grammar support (#2991)
|
2 лет назад |
Georgi Gerganov
|
e36ecdccc8
build : on Mac OS enable Metal by default (#2901)
|
2 лет назад |
Georgi Gerganov
|
47068e5170
speculative : PoC for speeding-up inference via speculative sampling (#2926)
|
2 лет назад |
Georgi Gerganov
|
8f429fa511
perplexity : fix ETA by warming up the model with an empty run
|
2 лет назад |
Cebtenzzre
|
ef15649972
build : fix most gcc and clang warnings (#2861)
|
2 лет назад |
staviq
|
8341a25957
main : log file (#2748)
|
2 лет назад |
xaedes
|
44c117f41e
train : mem usage and other improvements (#2439)
|
2 лет назад |
Johannes Gäßler
|
6b73ef1201
YAML result logging + preset script (#2657)
|
2 лет назад |
Georgi Gerganov
|
edd4c14817
llama : more tokenizer fixes (#2810)
|
2 лет назад |
Henri Vasserman
|
6bbc598a63
ROCm Port (#1087)
|
2 лет назад |
Georgi Gerganov
|
cf658adc83
llm : add Falcon support (#2717)
|
2 лет назад |
Kawrakow
|
62959e740e
Strided perplexity (#2714)
|
2 лет назад |
Johannes Gäßler
|
c63bb1d16a
CUDA: use mul_mat_q kernels by default (#2683)
|
2 лет назад |
slaren
|
1123f7fbdf
ggml-cuda : use graph allocator (#2684)
|
2 лет назад |
Georgi Gerganov
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
2 лет назад |