NVIDIA CosmosをGAT(DGX-H100)で動かそう

ssh -L 18000:localhost:18000 username@h100.gat.hogehoge
        

h100> export NGC_KEY=.......

h100> docker login nvcr.io
  Username: $oauthtoken （←この通り入力）
  Password: （←ここでもNGCトークンを入力）
  
  Login Succeeded ←成功時はこの表示です
  
  h100> docker pull nvcr.io/nim/nvidia/cosmos-predict1-7b-text2world:latest
  

#!/bin/bash
  
#毎回打つのが面倒な場合、鍵設定もスクリプトに含めます
#export NGC_API_KEY=.....
  
#NIMのキャッシュを置く場所
#無い場合はフォルダを事前に作成し、ユーザー権限でアクセスできるようにしておきます
export LOCAL_NIM_CACHE=/home/username/.cache
mkdir -p "$LOCAL_NIM_CACHE"
  
#dockerの起動
docker run -it --rm \
    --gpus all \
    --ipc host \
    -v "$LOCAL_NIM_CACHE:/opt/nim/.cache" \
    -u $(id -u) \
    -e NGC_API_KEY \
    -p 18000:8000 \
    nvcr.io/nim/nvidia/cosmos-predict1-7b-text2world:latest
  

INFO 2025-05-19 02:39:22.057] Serving endpoints:
  0.0.0.0:8000/v1/health/live (GET)
  0.0.0.0:8000/v1/health/ready (GET)
  0.0.0.0:8000/v1/metrics (GET)
  0.0.0.0:8000/v1/license (GET)
  0.0.0.0:8000/v1/metadata (GET)
  0.0.0.0:8000/v1/manifest (GET)
  0.0.0.0:8000/v1/infer (POST)
  INFO 2025-05-19 02:39:22.057] {'message': 'Starting HTTP Inference server', 'port': 8000, 'workers_count': 1, 'host': '0.0.0.0', 'log_level': 'info', 'SSL': 'disabled'}
  

#!/bin/bash
video_no=0
curl -X 'POST' \
'http://localhost:18000/v1/infer' \
   -H 'Accept: application/json' \
   -H 'Content-Type: application/json' \
   -d@- <<EOF > infer
{
         "prompt": "The video is captured from a camera mounted on a car. The camera is facing forward. The footage shows a quiet American street corner on a sunny day. A small diner with a retro sign stands at one corner, while the other corners feature low-rise office buildings and wide sidewalks. A single pickup truck waits at the intersection, with its brake lights visible with no visible movement. Suddenly, the car collides with the back of the truck.",
         "seed": 0
}
EOF
  
cat infer | jq -r ".b64_video" | base64 -d > video${video_no}.mp4
cat infer | jq -r ".upsampled_prompt" > upprompt${video_no}.txt