Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Commits on main

d25efe3
docs: update phi3-mini to phi4-mini (#9424)
aritra saha committed 1 year ago
a6f0f90
docs: add reins to community integrations (#9411)
İbrahim Çetin committed 1 year ago
3b1ddb2
1579c4f
build: install ccache manually in Dockerfile (#9464)
Jeffrey Morgan committed 1 year ago
e41c4cb
af68d60
ml: Enable support for flash attention
Jesse Gross committed 1 year ago
21aa666
ml: Empty tensor constructor for tensors
Jesse Gross committed 1 year ago
ee141cc
55e5776
854a919
e75c612
server/internal/internal/names: validate names (#9400)
Blake Mizerany committed 1 year ago
cda6f5c
bebb682
runner: defer context cancel
Michael Yang committed 1 year ago
31e472b
fix: replace deprecated functions
Michael Yang committed 1 year ago
657685e
a149128
cuda: enable flash attention
Michael Yang committed 1 year ago
b42aba4
25885e5
llama: add phi4 mini support (#9403)
Jeffrey Morgan committed 1 year ago
98d44fa
0c1041a
c245b04
kvcache: update tests
Michael Yang committed 1 year ago
8b194b7
ml: update Context.Forward interface
Michael Yang committed 1 year ago
3e8b8a1