Adrien Gallouët 3c62aed89f common : simplify etag tracking by removing json (#16342) 3 달 전
..
CMakeLists.txt 234e2ff8ed server : remove old LLAMA_SERVER_SSL (#16290) 3 달 전
arg.cpp 3c62aed89f common : simplify etag tracking by removing json (#16342) 3 달 전
arg.h 2d451c8059 common : add common_remote_get_content (#13123) 8 달 전
base64.hpp 381efbf480 llava : expose as a shared library for downstream projects (#3613) 2 년 전
build-info.cpp.in cc8d081879 cmake: Add ability to pass in LLAMA_BUILD_NUMBER/COMMIT (#14167) 7 달 전
chat-parser.cpp 3db4da56a5 chat : support Granite model reasoning and tool call (#14864) 5 달 전
chat-parser.h 3cb203c89f llama-chat : Do not throw when tool parsing fails (#14012) 7 달 전
chat.cpp bd0af02fc9 common : fix reasoning before forced tool call via tool_choice = required (#16264) 3 달 전
chat.h 88021565f0 chat : Deepseek V3.1 reasoning and tool calling support (OpenAI Style) (#15533) 4 달 전
common.cpp 624207e676 devops: add s390x & ppc64le CI (#15925) 3 달 전
common.h 835b2b915c model : add GroveMoE support (#15510) 3 달 전
console.cpp 8277a817f1 console : utf-8 fix for windows stdin (#9690) 1 년 전
console.h 6381d4e110 gguf : new file format with flexible meta data (beta) (#2398) 2 년 전
json-partial.cpp 53f925074d sync : vendor (#13901) 7 달 전
json-partial.h 53f925074d sync : vendor (#13901) 7 달 전
json-schema-to-grammar.cpp cd08fc3ecc common : Fix corrupted memory error on json grammar initialization (#16038) 4 달 전
json-schema-to-grammar.h 53f925074d sync : vendor (#13901) 7 달 전
llguidance.cpp 43dfd741a5 llguidance : set tokenizer slices to default (#13424) 8 달 전
log.cpp 408ff524b4 Implement --log-colors with always/never/auto (#15792) 4 달 전
log.h 408ff524b4 Implement --log-colors with always/never/auto (#15792) 4 달 전
ngram-cache.cpp 5bbe6a9fe9 ggml : portability fixes for VS 2017 (#12150) 10 달 전
ngram-cache.h 727368c60f llama : use LLAMA_TOKEN_NULL (#11062) 1 년 전
regex-partial.cpp 3198405e98 `common`: add partial regex support (#12808) 8 달 전
regex-partial.h 3198405e98 `common`: add partial regex support (#12808) 8 달 전
sampling.cpp e789095502 llama: print memory breakdown on exit (#15860) 3 달 전
sampling.h e92d53b29e sampling : optimize samplers by reusing bucket sort (#15665) 4 달 전
speculative.cpp e92d53b29e sampling : optimize samplers by reusing bucket sort (#15665) 4 달 전
speculative.h 94933c8c2e server : implement universal assisted decoding (#12635) 5 달 전