Revīziju vēsture

Autors SHA1 Ziņojums Datums
  Parth Sareen 0682dae027 sample: improve ollama engine sampler performance (#9374) 1 mēnesi atpakaļ
  Jesse Gross a7e63b82be ollamarunner: Improve multimodal input handling 1 mēnesi atpakaļ
  Jesse Gross b70fc4d51e model: Don't unconditionally add special tokens 1 mēnesi atpakaļ
  Michael Yang 05a01fdecb ml/backend/ggml: consolidate system info logging 2 mēneši atpakaļ
  Jesse Gross 21aa666a1e ml: Enable support for flash attention 2 mēneši atpakaļ
  Michael Yang 31e472baa4 runner: defer context cancel 2 mēneši atpakaļ
  Bruce MacDonald 0c1041ad85 runner: default to greedy sampler for performance (#9407) 2 mēneši atpakaļ
  Michael Yang d6af13efed runner: simplify tensor split parsing 2 mēneši atpakaļ
  Parth Sareen 0b7e1676eb sample: add sampling package for new engine (#8410) 2 mēneši atpakaļ
  Jesse Gross bd6a7d5e64 ollamarunner: Pass runner performance parameters to backends 2 mēneši atpakaļ
  Daniel Hiltgen df2680b4b9 Wire up system info log for new engine (#9123) 2 mēneši atpakaļ
  Jesse Gross ed443a0393 Runner for Ollama engine 4 mēneši atpakaļ