/
AI on K8s
Self-hosted AI inference for Kubernetes — pick your hardware, copy your deploy command.
GitHub ↗
Type
All
Models
Apps
Hardware
All
NVIDIA
AMD ROCm
Intel Arc
Tenstorrent
Max total VRAM
Any
≤ 16 GB
≤ 32 GB
≤ 80 GB
≤ 192 GB
≤ 640 GB
Category
All
Chat
Coding
Reasoning
Vision
MoE
Agent / UI
Topology
Single-node
Multi-node
Loading…
View on GitHub ↗