Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
launch: replace kimi-k2.5 with k2.6 as top recommended model (#15737)
2188357 Parth Sareen committed 7 months ago
mlxrunner: tokenize prompts in request handler goroutines
ce99f24 Jesse Gross committed 7 months ago
app/ui: fix model picker showing stale model after switching chats (#15280)
fb36a01 Matteo Celani committed 7 months ago
cmd: populate model capabilities in launchInteractiveModel (#15712)
0c65ed3 Michael Verrilli committed 7 months ago
server: apply format when think=false for gemma4 (#15678)
5d10216 Parth Sareen committed 7 months ago
launch: add kimi cli integration with installer flow (#15723)
8e05d73 Parth Sareen committed 7 months ago
cmd/launch: show WSL guidance on Windows instead of handing off (#15637)
57653b8 Parth Sareen committed 7 months ago
Merge pull request #15612 from ollama/drifkin/gemma4-split-templates
c88dae2 Devon Rifkin committed 7 months ago
Keep Gemma4 router projection in source precision (#15613)
5d920cc Daniel Hiltgen committed 7 months ago
mlx: fix RotatingKVCache.concat() dropping context on mid-rotation (#15591)
06ae636 Daniel Hiltgen committed 7 months ago
mlx: Improve gemma4 performance with fused operations (#15587)
48ad708 Daniel Hiltgen committed 7 months ago