Skip to content

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

Commits on main

discovery: fix cuda overlap case (#13176)
Daniel Hiltgen committed 1 year ago
dba62ff
Parser for Cogito v2 (#13145)
Grace committed 1 year ago
d70e935
deepseek2: upgrade to run v3+ models (#13166)
Michael Yang committed 1 year ago
5c1063d
cb485b2
chore: mark vulkan shaders as vendored files
Michael Yang committed 1 year ago
eac5b8b
kvcache: Use SetRows to store cache data
Jesse Gross committed 1 year ago
53985b3
b6e02cb
Renderer for Cogito v2 (#13139)
Grace committed 1 year ago
9193563
nomic-embed-text model implementation (#13071)
nicole pardal committed 1 year ago
8de30b5
win: exit instead of abort (#13138)
Daniel Hiltgen committed 1 year ago
485da9f
cuda: skip large batches
Michael Yang committed 1 year ago
0796d79
deepseekocr
Michael Yang committed 1 year ago
92981ae
docs: fix typo in vscode.mdx (#13116)
Lhiam Andrei Lingco committed 1 year ago
8ed1adf
440a382
migrate to golangci-lint v2 (#13109)
Michael Yang committed 1 year ago
718961d
330f62a
Add deepseek v3.1 (#13063)
Grace committed 1 year ago
584e2d6
2f36d76
399eacf
readme: add Kdeps to community integrations (#11877)
Joel Bryan Juliano committed 1 year ago
d564982
4cea757
a751bc1