Skip to content

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

Commits on main

8a75e9e
docs: update turbo model name (#11707)
Parth Sareen committed 1 year ago
4742e12
2d06977
tools: support anyOf types
Devon Rifkin committed 1 year ago
30f8a68
win: static link msvc libs (#11612)
Daniel Hiltgen committed 1 year ago
e378e33
gptoss: fix memory calc (#11700)
Michael Yang committed 1 year ago
fcec04b
docs: add docs for Ollama Turbo (#11687)
Jeffrey Morgan committed 1 year ago
ee92ca3
ggml: Prevent kv cache quanitization on gpt-oss
Jesse Gross committed 1 year ago
8253ad4
gpt-oss (#11672)
Michael Yang committed 1 year ago
fa7776f
0d38b66
kvcache: Enable SWA to retain additional entries
Jesse Gross committed 1 year ago
4183bb0
fixing broken AMD driver link (#11579)
Sajal Kulshreshtha committed 1 year ago
ff89ba9
Revert "CI: switch back to x86 macos builder" (#11588)
Daniel Hiltgen committed 1 year ago
6dcc5df
mac: disable bf16 on unsupported OS versions (#11585)
Daniel Hiltgen committed 1 year ago
25911a6
CI: switch back to x86 macos builder (#11572)
Daniel Hiltgen committed 1 year ago
8afa6e8
kvcache: Don't shift empty batches
Jesse Gross committed 1 year ago
c116a75
bbf66c0
kvcache: Group shift operations into batches
Jesse Gross committed 1 year ago
764be74
cli: catch upstream errors gracefully (#11512)
Patrick Devine committed 1 year ago
80b538e
tools: loosen tool argument parsing (#11509)
Jeffrey Morgan committed 1 year ago
4f8a016
1e6eab5
s#x/exp/maps#maps# (#11506)
Michael Yang committed 1 year ago
6c733bf
Fix GetModelInfo (#11496)
Patrick Devine committed 1 year ago
3bac5cb
Update linux.md (#11462)
ycomiti committed 1 year ago
4151ef8