| .. |
|
CMakeLists.txt
|
f32ca51bfe
server: add presets (config) when using multiple models (#17859)
|
vor 1 Monat |
|
arg.cpp
|
14931a826e
arg: fix order to use short form before long form (#18196)
|
vor 4 Wochen |
|
arg.h
|
4d5ae24c0a
arg: fix common_params_parse not accepting negated arg (#17991)
|
vor 1 Monat |
|
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-xml-toolcall.cpp
|
636fc17a37
Fix Kimi-K2 tool-call parsing issues (#17376)
|
vor 1 Monat |
|
chat-parser-xml-toolcall.h
|
636fc17a37
Fix Kimi-K2 tool-call parsing issues (#17376)
|
vor 1 Monat |
|
chat-parser.cpp
|
636fc17a37
Fix Kimi-K2 tool-call parsing issues (#17376)
|
vor 1 Monat |
|
chat-parser.h
|
1920345c3b
common : Generalized XML-style tool-call parsing with streaming support (GLM 4.5/4.6 + MiniMax M2 + SeedOSS + Kimi-K2 + Qwen3-Coder + Apriel-1.5 + Xiaomi-MiMo) (#16932)
|
vor 1 Monat |
|
chat-peg-parser.cpp
|
c05aa69f32
common : add nemotron 3 parsing (#18077)
|
vor 1 Monat |
|
chat-peg-parser.h
|
0a8026e768
common : introduce composable PEG parser combinators for chat parsing (#17136)
|
vor 1 Monat |
|
chat.cpp
|
c05aa69f32
common : add nemotron 3 parsing (#18077)
|
vor 1 Monat |
|
chat.h
|
190c4838bd
chat : reserve memory in compute_diffs and improve naming (#17729)
|
vor 1 Monat |
|
common.cpp
|
a2c199e479
common: clarify instructions for bug reports (#18134)
|
vor 1 Monat |
|
common.h
|
6ce3d85796
server: (webui) add --webui-config (#18028)
|
vor 1 Monat |
|
console.cpp
|
6c2131773c
cli: new CLI experience (#17824)
|
vor 1 Monat |
|
console.h
|
6c2131773c
cli: new CLI experience (#17824)
|
vor 1 Monat |
|
download.cpp
|
b8ee22cfde
common : add minimalist multi-thread progress bar (#17602)
|
vor 1 Monat |
|
download.h
|
ec18edfcba
server: introduce API for serving / loading / unloading multiple models (#17470)
|
vor 1 Monat |
|
http.h
|
4201deae9c
common: introduce http.h for httplib-based client (#16373)
|
vor 3 Monaten |
|
json-partial.cpp
|
1920345c3b
common : Generalized XML-style tool-call parsing with streaming support (GLM 4.5/4.6 + MiniMax M2 + SeedOSS + Kimi-K2 + Qwen3-Coder + Apriel-1.5 + Xiaomi-MiMo) (#16932)
|
vor 1 Monat |
|
json-partial.h
|
53f925074d
sync : vendor (#13901)
|
vor 7 Monaten |
|
json-schema-to-grammar.cpp
|
c05aa69f32
common : add nemotron 3 parsing (#18077)
|
vor 1 Monat |
|
json-schema-to-grammar.h
|
c05aa69f32
common : add nemotron 3 parsing (#18077)
|
vor 1 Monat |
|
llguidance.cpp
|
43dfd741a5
llguidance : set tokenizer slices to default (#13424)
|
vor 8 Monaten |
|
log.cpp
|
6c2131773c
cli: new CLI experience (#17824)
|
vor 1 Monat |
|
log.h
|
6c2131773c
cli: new CLI experience (#17824)
|
vor 1 Monat |
|
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 |
|
peg-parser.cpp
|
c05aa69f32
common : add nemotron 3 parsing (#18077)
|
vor 1 Monat |
|
peg-parser.h
|
0a8026e768
common : introduce composable PEG parser combinators for chat parsing (#17136)
|
vor 1 Monat |
|
preset.cpp
|
98c1c7a7bf
presets: refactor, allow cascade presets from different sources, add global section (#18169)
|
vor 4 Wochen |
|
preset.h
|
98c1c7a7bf
presets: refactor, allow cascade presets from different sources, add global section (#18169)
|
vor 4 Wochen |
|
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
|
4301e27319
common : restore grammar-based rejection sampling (#18137)
|
vor 1 Monat |
|
sampling.h
|
4301e27319
common : restore grammar-based rejection sampling (#18137)
|
vor 1 Monat |
|
speculative.cpp
|
4301e27319
common : restore grammar-based rejection sampling (#18137)
|
vor 1 Monat |
|
speculative.h
|
94933c8c2e
server : implement universal assisted decoding (#12635)
|
vor 5 Monaten |
|
unicode.cpp
|
0a8026e768
common : introduce composable PEG parser combinators for chat parsing (#17136)
|
vor 1 Monat |
|
unicode.h
|
0a8026e768
common : introduce composable PEG parser combinators for chat parsing (#17136)
|
vor 1 Monat |
Pascal
14931a826e
arg: fix order to use short form before long form (#18196)