15 lines
299 B
YAML
15 lines
299 B
YAML
apiVersion: v2
|
|
name: model-serving
|
|
version: 0.1.0
|
|
kubeVersion: ">=1.25.0"
|
|
description: Multi-model LLM serving (vLLM / SGLang / Ollama) with one API host & path routing
|
|
home: https://github.com/svc-design/artifacts
|
|
keywords:
|
|
- llm
|
|
- vllm
|
|
- sglang
|
|
- ollama
|
|
- cuda
|
|
- gpu
|
|
type: application
|