image: vllm/vllm-openai:latest

原始 JSON

{
  "kind": 1,
  "id": "cb158e6318dbb2cb9d1ddf33ca0d2a527004ae0f2a04ed4461ead3fe5ca734e3",
  "pubkey": "99bb5591c9116600f845107d31f9b59e2f7c7e09a1ff802e84f1d43da557ca64",
  "created_at": 1776544923,
  "tags": [
    [
      "alt",
      "A short note: image: vllm/vllm-openai:latest\n          command: ..."
    ],
    [
      "e",
      "00000452aff081b1c0cbd375f4388cdaac1c382817fe351ca756b899ea7403ab",
      "wss://relay.primal.net/",
      "root",
      "e2ccf7cf20403f3f2a4a55b328f0de3be38558a7d5f33632fdaaefc726c1c8eb"
    ],
    [
      "p",
      "99bb5591c9116600f845107d31f9b59e2f7c7e09a1ff802e84f1d43da557ca64",
      "wss://relay.damus.io/"
    ],
    [
      "p",
      "e2ccf7cf20403f3f2a4a55b328f0de3be38558a7d5f33632fdaaefc726c1c8eb",
      "wss://relay.bitcoinpark.com/"
    ],
    [
      "client",
      "Amethyst"
    ]
  ],
  "content": "image: vllm/vllm-openai:latest\n          command: [\"vllm\"]\n          env:\n            - name: VLLM_NO_USAGE_STATS\n              value: \"1\"\n            - name: VLLM_DO_NOT_TRACK\n              value: \"1\"\"\n          args:\n            - \"serve\"\n            - \"google/gemma-4-26B-A4B-it\"\n            - \"--host\"\n            - \"0.0.0.0\"\n            - \"--port\"\n            - \"8000\"\n            - \"--max-model-len\"\n            - \"262144\"\n            - \"--gpu-memory-utilization\"\n            - \"0.90\"\n            - \"--enable-auto-tool-choice\"\n            - \"--tool-call-parser\"\n            - \"gemma4\"\n            - \"--reasoning-parser\"\n            - \"gemma4\"\n\nDepending on how you deploy it you might need to adjust but this works for me (also with latest as v19.1 was released today)",
  "sig": "6df074e12181fccc9e93be0cda6b2185cd19304b07944b781a12febfabac0178bb3b29757fa988ac4d4885f8d8149e650cc9053a4438286c7faf9e4f9109a3d1"
}