Runtime marketplace

Deploy certified inference runtimes across distributed nodes.

UmamiEdge v6 introduces the marketplace framing: standardized runtime packs, compatibility tiers, health checks, model metadata, and node placement policies.

Runtime packTypeStatusModelsBest for
vLLM Runtime PackLLM servingreadyLlama, Qwen, Mistral, DeepSeek distilledhigh-throughput chat completions
Ollama Edge PackLocal model servingreadysmall/medium local modelspilot nodes and developer demos
TGI Enterprise PackText generationpilotHugging Face modelsenterprise-hosted inference
Embedding GatewayVector embeddingreadyBGE, E5, OpenAI-compatibleRAG and search workloads
Vision Inference PackVision AIplannedclassification, OCR, detectionagriculture, field ops, security review