Commit History

Author SHA1 Message Date
  Michael Yang f40b3de758 use int64 consistently 1 year ago
  Bruce MacDonald f221637053 first pass at linux gpu support (#454) 1 year ago
  Patrick Devine 790d24eb7b add show command (#474) 1 year ago
  Michael Yang 0f541a0367 s/ListResponseModel/ModelResponse/ 1 year ago
  Bruce MacDonald 42998d797d subprocess llama.cpp server (#401) 1 year ago
  Patrick Devine 8bbff2df98 add model IDs (#439) 1 year ago
  Michael Yang f723bf0879 ignore nil map values 1 year ago
  Michael Yang f27bc261cf s/parmeter/parameter/ 1 year ago
  Michael Yang 81d8d7b73f fix could not convert int 1 year ago
  Patrick Devine be989d89d1 Token auth (#314) 1 year ago
  Bruce MacDonald 4b3507f036 embeddings endpoint 1 year ago
  Bruce MacDonald 7a5f3616fd embed text document in modelfile 1 year ago
  Bruce MacDonald 21ddcaa1f1 pr comments 1 year ago
  Michael Yang f2074ed4c0 Merge pull request #306 from jmorganca/default-keep-system 1 year ago
  Jeffrey Morgan 8713ac23a8 allow overriding `template` and `system` in `/api/generate` 1 year ago
  Michael Yang 4dc5b117dd automatically set num_keep if num_keep < 0 1 year ago
  Michael Yang b9f4d67554 configurable rope frequency parameters 1 year ago
  Bruce MacDonald 1c5a8770ee read runner parameter options from map 1 year ago
  Jeffrey Morgan 528bafa585 cache loaded model 1 year ago
  Bruce MacDonald 184ad8f057 allow specifying stop conditions in modelfile 1 year ago
  Jeffrey Morgan 822a0e36eb lower batch size to 512 1 year ago
  Michael Yang fadf75f99d add stop conditions 1 year ago
  Michael Yang ad3a7d0e2c add NumGQA 1 year ago
  Jeffrey Morgan 688661ab9b increase default batch size to 1024 1 year ago
  Michael Yang cca61181cb sample metrics 1 year ago
  Michael Yang c490416189 lock on llm.lock(); decrease batch size 1 year ago
  Michael Yang f62a882760 add session expiration 1 year ago
  Michael Yang 3003fc03fc update predict code 1 year ago
  Michael Yang 32aec66e6a add load duration 1 year ago
  Michael Yang 35af37a2cb session id 1 year ago