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