Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
ollamarunner: Quiet debug logging and panic on unimplemented features
0daaaef Jesse Gross committed 1 year ago
ml/backend/ggml: update model loading for hybrid/multi backends
bab6f34 Michael Yang committed 1 year ago
llama: fix kv loading on snowflake-arctic-embed models (#9536)
4289c74 Jeffrey Morgan committed 1 year ago
server/internal/registry: take over pulls from server package (#9485)
e2252d0 Blake Mizerany committed 1 year ago
server/internal/registry: reintroduce pruning on model deletion (#9489)
7a01ad7 Blake Mizerany committed 1 year ago
server/.../backoff,syncs: don't break builds without synctest (#9484)
55ab9f3 Blake Mizerany committed 1 year ago