{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiavtnx6sqittkc6guj4hizgdeol5hlsl5b6otwnzpmb62gi4gmjdy",
"uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mk77edzitq52"
},
"path": "/t/cuda-error-802-on-every-h200-multi-gpu-hf-job-across-three-vllm-images/175419#post_4",
"publishedAt": "2026-04-23T22:04:26.000Z",
"site": "https://discuss.huggingface.co",
"textContent": "> Time-sensitive on my end , so any pointer on a flavor that works today would help most.\n\nIn that case, contact HF first anyway. via email is most reliable way: website@huggingface.co (and perhaps other address dedicated for Inference Endpoints? but generally this address is fine if vague.)",
"title": "CUDA Error 802 on every H200 multi-GPU HF Job, across three vLLM images"
}