Skip to content

A local-first multi-agent app development platform, built on PenguinHarness

863 B
Raw Blame
{
  "name": "@adelie/gpu-model-serving",
  "version": "0.6.8",
  "description": "Stand up an OpenAI-compatible LLM endpoint on a rented or owned GPU box: pick the instance, fetch and quantize weights, serve with SGLang — speculative decoding, prefix caching and tool calling for agent workloads — then verify it and expose the port.",
  "license": "Apache-2.0",
  "repository": {
    "type": "git",
    "url": "git+https://github.com/lmliheng/Adelie.git",
    "directory": "plugins/gpu-model-serving"
  },
  "keywords": [
    "adelie-plugin",
    "penguin-harness",
    "gpu",
    "llm",
    "sglang",
    "inference",
    "serving",
    "openai-compatible",
    "quantization",
    "speculative-decoding"
  ],
  "files": [
    "plugin.json",
    "icon.svg",
    "README.md",
    "skills",
    "LICENSE"
  ],
  "publishConfig": {
    "access": "public"
  }
}