| .. |
|
CMakeLists.txt
|
a457551332
cmake : do not search for curl libraries by ourselves (#14613)
|
vor 6 Monaten |
|
arg.cpp
|
22ee5a971b
Add gate_sigmoid to callback
|
vor 3 Monaten |
|
arg.h
|
2d451c8059
common : add common_remote_get_content (#13123)
|
vor 8 Monaten |
|
base64.hpp
|
381efbf480
llava : expose as a shared library for downstream projects (#3613)
|
vor 2 Jahren |
|
build-info.cpp.in
|
cc8d081879
cmake: Add ability to pass in LLAMA_BUILD_NUMBER/COMMIT (#14167)
|
vor 7 Monaten |
|
chat-parser.cpp
|
3db4da56a5
chat : support Granite model reasoning and tool call (#14864)
|
vor 5 Monaten |
|
chat-parser.h
|
3cb203c89f
llama-chat : Do not throw when tool parsing fails (#14012)
|
vor 7 Monaten |
|
chat.cpp
|
88021565f0
chat : Deepseek V3.1 reasoning and tool calling support (OpenAI Style) (#15533)
|
vor 4 Monaten |
|
chat.h
|
88021565f0
chat : Deepseek V3.1 reasoning and tool calling support (OpenAI Style) (#15533)
|
vor 4 Monaten |
|
common.cpp
|
e81b8e4b7f
llama: use FA + max. GPU layers by default (#15434)
|
vor 4 Monaten |
|
common.h
|
22ee5a971b
Add gate_sigmoid to callback
|
vor 3 Monaten |
|
console.cpp
|
8277a817f1
console : utf-8 fix for windows stdin (#9690)
|
vor 1 Jahr |
|
console.h
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
vor 2 Jahren |
|
json-partial.cpp
|
53f925074d
sync : vendor (#13901)
|
vor 7 Monaten |
|
json-partial.h
|
53f925074d
sync : vendor (#13901)
|
vor 7 Monaten |
|
json-schema-to-grammar.cpp
|
cd08fc3ecc
common : Fix corrupted memory error on json grammar initialization (#16038)
|
vor 4 Monaten |
|
json-schema-to-grammar.h
|
53f925074d
sync : vendor (#13901)
|
vor 7 Monaten |
|
llguidance.cpp
|
43dfd741a5
llguidance : set tokenizer slices to default (#13424)
|
vor 8 Monaten |
|
log.cpp
|
408ff524b4
Implement --log-colors with always/never/auto (#15792)
|
vor 4 Monaten |
|
log.h
|
408ff524b4
Implement --log-colors with always/never/auto (#15792)
|
vor 4 Monaten |
|
ngram-cache.cpp
|
5bbe6a9fe9
ggml : portability fixes for VS 2017 (#12150)
|
vor 10 Monaten |
|
ngram-cache.h
|
727368c60f
llama : use LLAMA_TOKEN_NULL (#11062)
|
vor 1 Jahr |
|
regex-partial.cpp
|
3198405e98
`common`: add partial regex support (#12808)
|
vor 8 Monaten |
|
regex-partial.h
|
3198405e98
`common`: add partial regex support (#12808)
|
vor 8 Monaten |
|
sampling.cpp
|
e92d53b29e
sampling : optimize samplers by reusing bucket sort (#15665)
|
vor 4 Monaten |
|
sampling.h
|
e92d53b29e
sampling : optimize samplers by reusing bucket sort (#15665)
|
vor 4 Monaten |
|
speculative.cpp
|
e92d53b29e
sampling : optimize samplers by reusing bucket sort (#15665)
|
vor 4 Monaten |
|
speculative.h
|
94933c8c2e
server : implement universal assisted decoding (#12635)
|
vor 5 Monaten |
Piotr Wilkin
22ee5a971b
Add gate_sigmoid to callback