Georgi Gerganov 3ce30e07c9 llama : pass KV cache type through API

2023-12-05 15:40:23 +02:00

..

base64.hpp

llava : expose as a shared library for downstream projects (#3613)

2023-11-07 00:36:23 +03:00

build-info.cpp.in

build : link against build info instead of compiling against it (#3879)

2023-11-02 08:50:16 +02:00

CMakeLists.txt

build : fix build info generation and cleanup Makefile (#3920)

2023-12-01 00:23:08 +02:00

common.cpp

llama : pass KV cache type through API

2023-12-05 15:40:23 +02:00

common.h

llama : pass KV cache type through API

2023-12-05 15:40:23 +02:00

console.cpp

…

console.h

…

grammar-parser.cpp

ggml : fix rope + llama minor optimizations (#3560)

2023-10-20 13:02:12 +03:00

grammar-parser.h

…

log.h

log : make generating separate log files optional (#3787)

2023-11-01 16:18:27 +02:00

sampling.cpp

sampling : null grammar field after reset (#3885)

2023-11-01 15:40:43 +02:00

sampling.h

samplers : Min-P sampler implementation [alternative to Top P/Top K] (#3841)

2023-10-31 20:44:49 +01:00

stb_image.h

…

train.cpp

train : move number of gpu layers argument parsing to common/train.cpp (#4074)

2023-11-17 17:19:16 +02:00

train.h

sync : ggml (backend v2) (#3912)

2023-11-13 14:16:23 +02:00