تاریخچه Commit ها

نویسنده SHA1 پیام تاریخ
  ParthSareen 4450f871db wip 1 ماه پیش
  ParthSareen 5ec6bb52a0 prototyping 1 ماه پیش
  Michael Yang 74bd09652d ml/backend/ggml: load tensors in 32KiB chunks 1 ماه پیش
  Jesse Gross 3ed7ad3ab3 kvcache: Pass granular cache size into implementations 1 ماه پیش
  Jesse Gross 0ff28758b3 ollamarunner: Provide mechanism for backends to report loading progress 1 ماه پیش
  Jesse Gross 0fbfcf3c9c model: Pass input tensor instead of raw data to models 1 ماه پیش
  Jesse Gross 0c220935bd input: Rename Options to Batch 1 ماه پیش
  Jesse Gross bf24498b1e ollamarunner: Check for minBatch of context space when shifting 1 ماه پیش
  Bruce MacDonald 95e271d98f runner: remove cache prompt flag from ollama runner (#9826) 1 ماه پیش
  Jesse Gross 282bfaaa95 ollamarunner: Use a separate context per multimodal input 2 ماه پیش
  Jesse Gross 9679f40146 ml: Allow models to constrain inputs to a single batch 2 ماه پیش
  Bruce MacDonald 3892c3a703 llm: remove internal subprocess req and resp types (#9324) 2 ماه پیش
  Michael Yang ec46f3286c engine: error on embeddings; not currently implemented 2 ماه پیش
  Jeffrey Morgan e093db92c4 sample: temporarily use grammars for constrained generation in new engine (#9586) 2 ماه پیش
  Jesse Gross a1cda80bcb model: Update encoder cache to use multimodal input processing handler 2 ماه پیش
  Jesse Gross 4614fafae0 ollamarunner: Don't panic for unimplemented features at runtime. 2 ماه پیش
  Jesse Gross 0daaaef8c9 ollamarunner: Quiet debug logging and panic on unimplemented features 2 ماه پیش
  Parth Sareen 0682dae027 sample: improve ollama engine sampler performance (#9374) 2 ماه پیش
  Jesse Gross a7e63b82be ollamarunner: Improve multimodal input handling 2 ماه پیش
  Jesse Gross b70fc4d51e model: Don't unconditionally add special tokens 2 ماه پیش
  Michael Yang 05a01fdecb ml/backend/ggml: consolidate system info logging 2 ماه پیش
  Jesse Gross 21aa666a1e ml: Enable support for flash attention 2 ماه پیش
  Michael Yang 31e472baa4 runner: defer context cancel 2 ماه پیش
  Bruce MacDonald 0c1041ad85 runner: default to greedy sampler for performance (#9407) 2 ماه پیش
  Michael Yang d6af13efed runner: simplify tensor split parsing 2 ماه پیش
  Parth Sareen 0b7e1676eb sample: add sampling package for new engine (#8410) 2 ماه پیش
  Jesse Gross bd6a7d5e64 ollamarunner: Pass runner performance parameters to backends 2 ماه پیش
  Daniel Hiltgen df2680b4b9 Wire up system info log for new engine (#9123) 2 ماه پیش
  Jesse Gross ed443a0393 Runner for Ollama engine 4 ماه پیش