 Georgi Gerganov
|
986b6ce9f9
ggml, llama : avoid heavy V transpose + improvements (#775)
|
há 2 anos atrás |
 Marian Cepok
|
c0bb1d3ce2
ggml : change ne to int64_t (#626)
|
há 2 anos atrás |
 Justine Tunney
|
6f23ba5ee2
Ensure --mlock works properly with mmap() support
|
há 2 anos atrás |
 Slaren
|
c03ae8dca1
Add mmap support for model files
|
há 2 anos atrás |
 Stephan Walter
|
c1f885067c
ggml : introduce structs for the q4 data blocks (#356)
|
há 2 anos atrás |
 comex
|
563cdc391d
Support calling mlock() on loaded model data on Linux and macOS (#453)
|
há 2 anos atrás |
|
Stephan Walter
|
69c92298a9
Deduplicate q4 quantization functions (#383)
|
há 2 anos atrás |
|
Georgi Gerganov
|
f5a77a629b
Introduce C-style API (#370)
|
há 2 anos atrás |
 hoangmit
|
6eac39ba95
Add RMS norm and use it (#187)
|
há 2 anos atrás |
|
Georgi Gerganov
|
26c0846629
Initial release
|
há 2 anos atrás |
