 Michael Yang
|
5827999e9e
next ollama runner
|
há 5 meses atrás |
 isamu arimoto
|
6ae2adc1af
openai: accept additional headers to fix CORS errors (#8343)
|
há 4 meses atrás |
 Patrick Devine
|
86a622cbdc
Update the /api/create endpoint to use JSON (#7935)
|
há 4 meses atrás |
 湛露先生
|
928de9050e
server: reuse InvalidModelNameErrMsg type (#8163)
|
há 4 meses atrás |
|
Patrick Devine
|
8c9fb8eb73
imageproc mllama refactor (#7537)
|
há 4 meses atrás |
 Blake Mizerany
|
b1fd7fef86
server: more support for mixed-case model names (#8017)
|
há 4 meses atrás |
 frob
|
757eeacc1b
server: lowercase hostname for Host header check (#5851)
|
há 4 meses atrás |
 Daniel Hiltgen
|
4879a234c4
build: Make target improvements (#7499)
|
há 4 meses atrás |
 Parth Sareen
|
c6c526275d
api: add generate endpoint for structured outputs (#7939)
|
há 5 meses atrás |
|
Parth Sareen
|
630e7dc6ff
api: structured outputs - chat endpoint (#7900)
|
há 5 meses atrás |
 Jeffrey Morgan
|
d543b282a7
server: add warning message for deprecated context field (#7878)
|
há 5 meses atrás |
|
Parth Sareen
|
5f8051180e
Enable index tracking for tools - openai api support (#7888)
|
há 5 meses atrás |
|
Parth Sareen
|
ce7455a8e1
api: enable tool streaming (#7836)
|
há 5 meses atrás |
 oza6ut0ne
|
31cb1ca9e5
openai: accept X-Stainless-Retry-Count header (#6910)
|
há 5 meses atrás |
|
Daniel Hiltgen
|
f602ab4de4
expose underlying error on embedding failure (#7743)
|
há 5 meses atrás |
|
Blake Mizerany
|
4b8a2e341a
server: allow mixed-case model names on push, pull, cp, and create (#7676)
|
há 5 meses atrás |
|
Daniel Hiltgen
|
a4c70fe157
One corrupt manifest should not wedge model operations (#7515)
|
há 6 meses atrás |
|
Daniel Hiltgen
|
4ebfa2cb91
Quiet down debug log of image payload (#7454)
|
há 6 meses atrás |
 Jesse Gross
|
c826e57475
runner.go: Better abstract vision model integration
|
há 6 meses atrás |
|
Patrick Devine
|
084929c293
add mllama image processing to the generate handler (#7384)
|
há 6 meses atrás |
|
Patrick Devine
|
c7cb0f0602
image processing for llama3.2 (#6963)
|
há 6 meses atrás |
|
Daniel Hiltgen
|
05cd82ef94
Rename gpu package discover (#7143)
|
há 6 meses atrás |
 Alex Mavrogiannis
|
f40bb398f6
Stop model before deletion if loaded (fixed #6957) (#7050)
|
há 7 meses atrás |
|
Daniel Hiltgen
|
cd5c8f6471
Optimize container images for startup (#6547)
|
há 7 meses atrás |
|
Patrick Devine
|
abed273de3
add "stop" command (#6739)
|
há 7 meses atrás |
|
Jeffrey Morgan
|
47fa0839b9
server: clean up route names for consistency (#6524)
|
há 8 meses atrás |
 royjhan
|
8b00a415ab
Load Embedding Model on Empty Input (#6325)
|
há 8 meses atrás |
|
Jeffrey Morgan
|
15c2d8fe14
server: parallelize embeddings in API web handler instead of in subprocess runner (#6220)
|
há 9 meses atrás |
|
Jesse Gross
|
1829fb61bd
manifest: Fix crash on startup when trying to clean up unused files (#5840)
|
há 9 meses atrás |
|
Michael Yang
|
b732beba6a
lint
|
há 9 meses atrás |
