| .. |
|
CMakeLists.txt
|
a457551332
cmake : do not search for curl libraries by ourselves (#14613)
|
il y a 6 mois |
|
arg.cpp
|
9ebebef62f
llama : remove KV cache defragmentation logic (#15473)
|
il y a 4 mois |
|
arg.h
|
2d451c8059
common : add common_remote_get_content (#13123)
|
il y a 8 mois |
|
base64.hpp
|
381efbf480
llava : expose as a shared library for downstream projects (#3613)
|
il y a 2 ans |
|
build-info.cpp.in
|
cc8d081879
cmake: Add ability to pass in LLAMA_BUILD_NUMBER/COMMIT (#14167)
|
il y a 7 mois |
|
chat-parser.cpp
|
3db4da56a5
chat : support Granite model reasoning and tool call (#14864)
|
il y a 5 mois |
|
chat-parser.h
|
3cb203c89f
llama-chat : Do not throw when tool parsing fails (#14012)
|
il y a 7 mois |
|
chat.cpp
|
657b8a77bd
chat: handle gpt-oss return/end token inconsistency (#15421)
|
il y a 4 mois |
|
chat.h
|
f75b830647
chat : include kwargs in template example (#15309)
|
il y a 5 mois |
|
common.cpp
|
9ebebef62f
llama : remove KV cache defragmentation logic (#15473)
|
il y a 4 mois |
|
common.h
|
9ebebef62f
llama : remove KV cache defragmentation logic (#15473)
|
il y a 4 mois |
|
console.cpp
|
8277a817f1
console : utf-8 fix for windows stdin (#9690)
|
il y a 1 an |
|
console.h
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
il y a 2 ans |
|
json-partial.cpp
|
53f925074d
sync : vendor (#13901)
|
il y a 7 mois |
|
json-partial.h
|
53f925074d
sync : vendor (#13901)
|
il y a 7 mois |
|
json-schema-to-grammar.cpp
|
40bfa04c95
common : use std::string_view now that we target c++17 (#14319)
|
il y a 6 mois |
|
json-schema-to-grammar.h
|
53f925074d
sync : vendor (#13901)
|
il y a 7 mois |
|
llguidance.cpp
|
43dfd741a5
llguidance : set tokenizer slices to default (#13424)
|
il y a 8 mois |
|
log.cpp
|
bfd11a2344
Fix: Compile failure due to Microsoft STL breaking change (#11836)
|
il y a 11 mois |
|
log.h
|
fef0cbeadf
cleanup: fix compile warnings associated with gnu_printf (#11811)
|
il y a 11 mois |
|
ngram-cache.cpp
|
5bbe6a9fe9
ggml : portability fixes for VS 2017 (#12150)
|
il y a 10 mois |
|
ngram-cache.h
|
727368c60f
llama : use LLAMA_TOKEN_NULL (#11062)
|
il y a 1 an |
|
regex-partial.cpp
|
3198405e98
`common`: add partial regex support (#12808)
|
il y a 8 mois |
|
regex-partial.h
|
3198405e98
`common`: add partial regex support (#12808)
|
il y a 8 mois |
|
sampling.cpp
|
f5cd27b71d
`server`: streaming of tool calls and thoughts when `--jinja` is on (#12379)
|
il y a 7 mois |
|
sampling.h
|
ff227703d6
sampling : support for llguidance grammars (#10224)
|
il y a 11 mois |
|
speculative.cpp
|
94933c8c2e
server : implement universal assisted decoding (#12635)
|
il y a 5 mois |
|
speculative.h
|
94933c8c2e
server : implement universal assisted decoding (#12635)
|
il y a 5 mois |
Georgi Gerganov
9ebebef62f
llama : remove KV cache defragmentation logic (#15473)