Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
server: parallelize embeddings in API web handler instead of in subprocess runner (#6220)
15c2d8f Jeffrey Morgan committed 2 years ago
llm: prevent loading too large models on windows (#5926)
25906d7 Daniel Hiltgen committed 2 years ago
Merge pull request #6235 from Nicholas42/fix_line_endings
97fae2d Michael Yang committed 2 years ago
manifest: Store layers inside manifests consistently as values.
7edaf6e Jesse Gross committed 2 years ago
manifest: Fix crash on startup when trying to clean up unused files (#5840)
1829fb6 Jesse Gross committed 2 years ago