Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
Make sure all launchers know about cloud model metadata (#19223)
4568674 J Berg committed 27 days ago
server: read loaded runner models without refMu (#19070)
52f1681 Daniel Hiltgen committed 1 month ago
avoid scary claude warning about auto compact window being too big
b5c4e90 Jonathan Berg committed 1 month ago
server: cancel remote inference when clients disconnect (#19144)
4ed3ba1 Eva H committed 1 month ago
api: populate show renderer/parser fields and add template_source (#19095)
36a6e99 Daniel Hiltgen committed 1 month ago
llama-server: let llama-server infer the draft speculative type (#19064)
e51196f Daniel Hiltgen committed 1 month ago
transfer: support proxies on registry redirect targets (#19065)
4d2e250 Patrick Devine committed 1 month ago