| .. |
|
CMakeLists.txt
|
4201deae9c
common: introduce http.h for httplib-based client (#16373)
|
há 3 meses atrás |
|
arg.cpp
|
f6dcda3900
server : context checkpointing for hybrid and recurrent models (#16382)
|
há 3 meses atrás |
|
arg.h
|
364a7a6d4a
common : remove common_has_curl() (#16351)
|
há 3 meses atrás |
|
base64.hpp
|
381efbf480
llava : expose as a shared library for downstream projects (#3613)
|
há 2 anos atrás |
|
build-info.cpp.in
|
cc8d081879
cmake: Add ability to pass in LLAMA_BUILD_NUMBER/COMMIT (#14167)
|
há 7 meses atrás |
|
chat-parser.cpp
|
34fcc5a4ac
model : Apertus model implementation (#15852)
|
há 3 meses atrás |
|
chat-parser.h
|
34fcc5a4ac
model : Apertus model implementation (#15852)
|
há 3 meses atrás |
|
chat.cpp
|
128d522c04
chat : support Magistral thinking (#16413)
|
há 3 meses atrás |
|
chat.h
|
128d522c04
chat : support Magistral thinking (#16413)
|
há 3 meses atrás |
|
common.cpp
|
624207e676
devops: add s390x & ppc64le CI (#15925)
|
há 3 meses atrás |
|
common.h
|
f6dcda3900
server : context checkpointing for hybrid and recurrent models (#16382)
|
há 3 meses atrás |
|
console.cpp
|
8277a817f1
console : utf-8 fix for windows stdin (#9690)
|
há 1 ano atrás |
|
console.h
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
há 2 anos atrás |
|
http.h
|
4201deae9c
common: introduce http.h for httplib-based client (#16373)
|
há 3 meses atrás |
|
json-partial.cpp
|
53f925074d
sync : vendor (#13901)
|
há 7 meses atrás |
|
json-partial.h
|
53f925074d
sync : vendor (#13901)
|
há 7 meses atrás |
|
json-schema-to-grammar.cpp
|
cd08fc3ecc
common : Fix corrupted memory error on json grammar initialization (#16038)
|
há 4 meses atrás |
|
json-schema-to-grammar.h
|
53f925074d
sync : vendor (#13901)
|
há 7 meses atrás |
|
llguidance.cpp
|
43dfd741a5
llguidance : set tokenizer slices to default (#13424)
|
há 8 meses atrás |
|
log.cpp
|
408ff524b4
Implement --log-colors with always/never/auto (#15792)
|
há 4 meses atrás |
|
log.h
|
408ff524b4
Implement --log-colors with always/never/auto (#15792)
|
há 4 meses atrás |
|
ngram-cache.cpp
|
5bbe6a9fe9
ggml : portability fixes for VS 2017 (#12150)
|
há 10 meses atrás |
|
ngram-cache.h
|
727368c60f
llama : use LLAMA_TOKEN_NULL (#11062)
|
há 1 ano atrás |
|
regex-partial.cpp
|
3198405e98
`common`: add partial regex support (#12808)
|
há 8 meses atrás |
|
regex-partial.h
|
3198405e98
`common`: add partial regex support (#12808)
|
há 8 meses atrás |
|
sampling.cpp
|
e789095502
llama: print memory breakdown on exit (#15860)
|
há 3 meses atrás |
|
sampling.h
|
e92d53b29e
sampling : optimize samplers by reusing bucket sort (#15665)
|
há 4 meses atrás |
|
speculative.cpp
|
e92d53b29e
sampling : optimize samplers by reusing bucket sort (#15665)
|
há 4 meses atrás |
|
speculative.h
|
94933c8c2e
server : implement universal assisted decoding (#12635)
|
há 5 meses atrás |
Pascal
128d522c04
chat : support Magistral thinking (#16413)