Skip to main content
NVIDIA
vLLM Model-Free NIM
Container
NVIDIA
vLLM Model-Free NIM

The vLLM Model-Free NIM is an inference container for running compatible customer-provided models with NVIDIA GPU acceleration.

LayerLabelCreated
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4CMD
—
09/02/2026 3:30 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
/opt/nim/start_server.sh
09/02/2026 3:30 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
nvs:1000
09/02/2026 3:30 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NIM_BACKEND_PORT=8001
09/02/2026 3:30 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NIM_SERVER_PORT=8000
09/02/2026 3:30 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
SERVER_START_SCRIPT_PATH=/opt/nim/start_server.sh
09/02/2026 3:30 PM UTC
sha256:b10274cd80909aaa62cb98a9e1ac3f2219541c549619fa28b61dd267442b1d7bRUN
BASE_IMAGE=nvcr.io/0886876425485018/brightdelta-real/china-vllm-basecontainer-stage2:6faf99d3cd BACKEND_TYPE=vllm NIM_STACK_COMMIT=5cdb9426c18fd143711c226d9bf0d8f74d528010 TELEMETRY_MODE=0 TELEMETRY_ENDPOINT=0 PIP_INDEX_URL=https://pypi.org/simple NIM_CACHE_PATH=/opt/nim/.cache /bin/bash -o pipefail -c chmod +x /opt/nim/start_server.sh /opt/nim/scripts/generate_nginx_config.sh &&
  chmod 0755 /opt/nim/scripts/runtime_cache_contract.sh &&
  bash -n /opt/nim/scripts/runtime_cache_contract.sh &&
  mkdir -p /opt/nim/.cache /opt/nim/nginx /opt/nim/generated_configs &&
  chown -R 1000.1000 /opt/nim &&
  install -d -o 1000 -g 1000 -m 0755 /opt/nim/.cache/tmp /opt/nim/.cache/huggingface/hub /opt/nim/runtime-cache "/opt/nim/runtime-cache/${BACKEND_TYPE}/cache" "/opt/nim/runtime-cache/${BACKEND_TYPE}/config" /opt/nim/runtime-cache/torchinductor /opt/nim/runtime-cache/triton &&
  chown 0:0 /opt/nim/LICENSE &&
  chmod 0444 /opt/nim/LICENSE &&
  grep -q "NVIDIA Software License Agreement" /opt/nim/LICENSE &&
  grep -q "Product-Specific Terms for NVIDIA AI Products" /opt/nim/LICENSE &&
  ! grep -q "NVIDIA AI Product Agreement" /opt/nim/LICENSE
09/02/2026 3:30 PM UTC
sha256:732cb27feb7014152bd8014f017f7b40605967f95842570222166b06ccfaf00dCOPY
docker/start_server.sh /opt/nim/start_server.sh
09/02/2026 3:30 PM UTC
sha256:6a82436177097abdb7e0f31f74ac71127d42ab8b003167bce362e0126d557d30COPY
docker/scripts/runtime_cache_contract.sh /opt/nim/scripts/runtime_cache_contract.sh
09/02/2026 3:30 PM UTC
sha256:1f602510ce3c803b536a4ddc3445e8b04dac2be568e235acedc53ce9dea65a3dCOPY
nginx /opt/nim/scripts
09/02/2026 3:30 PM UTC
...

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.