Histórico de Commits

Autor SHA1 Mensagem Data
  Pascal 128d522c04 chat : support Magistral thinking (#16413) há 3 meses atrás
  Piotr Wilkin (ilintar) 34fcc5a4ac model : Apertus model implementation (#15852) há 3 meses atrás
  shun095 f432d8d83e chat: Fix streaming parser for granite models (#15682) há 4 meses atrás
  Jesse 88021565f0 chat : Deepseek V3.1 reasoning and tool calling support (OpenAI Style) (#15533) há 4 meses atrás
  Piotr Wilkin (ilintar) b2426e469e chat : nemotron thinking & toolcalling support (#15676) há 4 meses atrás
  Piotr Wilkin (ilintar) 60e5eee31f chat : Seed OSS thinking + tool call support (#15552) há 4 meses atrás
  Xuan-Son Nguyen e9288e8869 chat : clarify the meaning of reasoning_format (#15408) há 5 meses atrás
  Aldehir Rojas b204a5a234 gpt-oss: implement harmony parsing (#15181) há 5 meses atrás
  Sachin Desai 3db4da56a5 chat : support Granite model reasoning and tool call (#14864) há 5 meses atrás
  Jhen-Jie Hong f738989dcb chat : fix multiple tool_calls on hermes-2-pro (#14962) há 5 meses atrás
  Diego Devesa 7f4fbe5183 llama : allow building all tests on windows when not using shared libs (#13980) há 7 meses atrás
  Olivier Chafik c9bbc77931 `server`: update deepseek reasoning format (pass reasoning_content as diffs) (#13933) há 7 meses atrás
  Olivier Chafik e15898d1c7 server: allow unclosed thinking tags (#13931) há 7 meses atrás
  Georgi Gerganov 53f925074d sync : vendor (#13901) há 7 meses atrás
  Olivier Chafik 03f582ae8f server: fix streaming crashes (#13786) há 7 meses atrás
  Olivier Chafik d74e94c1b3 `server`: fix format of streamed tool call deltas (diff name, fix id location) (#13800) há 7 meses atrás
  Olivier Chafik e121edc432 `server`: add `--reasoning-budget 0` to disable thinking (incl. qwen3 w/ enable_thinking:false) (#13771) há 7 meses atrás
  Olivier Chafik f5cd27b71d `server`: streaming of tool calls and thoughts when `--jinja` is on (#12379) há 7 meses atrás
  Olivier Chafik aa48e373f2 `server`: inject date_string in llama 3.x template + fix date for firefunction v2 (#12802) há 8 meses atrás
  Georgi Gerganov 13b4548877 cmake : do not include ./src as public for libllama (#13062) há 8 meses atrás
  Olivier Chafik b6930ebc42 `tool-call`: fix non-tool-calling grammar crashes w/ Qwen / Hermes 2 templates (#12900) há 9 meses atrás
  Olivier Chafik 4e39a3c332 `server`: extract <think> tags from qwq outputs (#12297) há 10 meses atrás
  Olivier Chafik 87c2630546 allow missing content in message if tool_calls provided (#12293) há 10 meses atrás
  Olivier Chafik 669912d9a5 `tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034) há 10 meses atrás
  Olivier Chafik 63e489c025 tool-call: refactor common chat / tool-call api (+ tests / fixes) (#11900) há 11 meses atrás
  Olivier Chafik c7f460ab88 `server`: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless `--reasoning-format none` (#11607) há 11 meses atrás
  Olivier Chafik 9f4cc8f8d3 `sync`: minja (#11641) há 11 meses atrás
  Olivier Chafik db288b60cb `tool-call`: command r7b fix for normal responses (#11608) há 11 meses atrás
  Olivier Chafik bfcce4d693 `tool-call`: support Command R7B (+ return tool_plan "thoughts" in API) (#11585) há 11 meses atrás
  Olivier Chafik 8b576b6c55 Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639) há 11 meses atrás