Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
build: install binutils alongside gcc in Dockerfile (#9475)
1579c4f Jeffrey Morgan committed 1 year ago
server/internal/client/ollama: hold DiskCache on Registry (#9463)
3519dd1 Blake Mizerany committed 1 year ago
server/internal/client/ollama: handle extended names in client/ollama (#9454)
ee048b7 Blake Mizerany committed 1 year ago
build: use correct GGML_HIP_NO_VMM compiler definition for ggml-hip (#9451)
96a97ad Jeffrey Morgan committed 1 year ago
server: validate local path on safetensor create (#9379)
bebb682 Bruce MacDonald committed 1 year ago
build: add compute capability 12.0 to CUDA 12 preset (#9426)
a149128 Jeffrey Morgan committed 1 year ago
server/.../safetensors: fix offsets and include all model parts (#9427)
eed11de Blake Mizerany committed 1 year ago
CONTRIBUTING: provide clarity on good commit messages, and bad (#9405)
2099e2d Blake Mizerany committed 1 year ago
runner: default to greedy sampler for performance (#9407)
0c1041a Bruce MacDonald committed 1 year ago
server/internal/registry: implement CloseNotify and Flush (for now) (#9402)
41dc280 Blake Mizerany committed 1 year ago