ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
GPT-OSS-20B
Container
NVIDIA
NVIDIA
GPT-OSS-20B

NVIDIA NIM for GPU accelerated GPT-OSS-20B Model inference through OpenAI compatible APIs

NVIDIA AI Enterprise SupportedNVIDIA NIM
LayerLabelCreated
sha256:13ab07cf6b428792e7a7d49fc78da4ed59905ad447cf02d598014106ef0c60d4COPY
./docker/nim/NSPECT-SW5U-LCYW/notices/* /opt/nim/
10/14/2025 8:44 PM UTC
sha256:9401dead44c628ce9e322748a926d0ca87945f5adb6fc2ce95a8e41820a98a00COPY
./docker/nim/NSPECT-SW5U-LCYW/banner.txt /opt/nvidia/entrypoint.d/31-model-license.txt
10/14/2025 8:44 PM UTC
sha256:6225379e6b1f066ed7876a3d3bb5a9adc6bb0b68b75f4d7dc0ab2290a320c14bCOPY
./docker/nim/NSPECT-SW5U-LCYW/LICENSE /opt/nim/MODEL_LICENSE
10/14/2025 8:44 PM UTC
sha256:b172b0c29941951c546652ff29349987babea23a51765f399a401c928223eba8RUN
NIM_USER_ID=1000 NIM_MODEL_NAME=openai/gpt-oss-20b NIM_VERSION=1.12.4 NIM_NSPECT_ID=NSPECT-LJGD-9W15 NIM_MODEL_NSPECT_ID=NSPECT-SW5U-LCYW NIM_FORCE_TRUST_REMOTE_CODE=0 ln -s /opt/nim/etc/default/model_manifest.yaml /etc/nim/config/model_manifest.yaml
10/14/2025 8:44 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
1000
10/14/2025 8:44 PM UTC
sha256:9253d771831cccd44467f6768904567c9dfed7961c37b81efff26d58acba9bffRUN
NIM_USER_ID=1000 NIM_MODEL_NAME=openai/gpt-oss-20b NIM_VERSION=1.12.4 NIM_NSPECT_ID=NSPECT-LJGD-9W15 NIM_MODEL_NSPECT_ID=NSPECT-SW5U-LCYW NIM_FORCE_TRUST_REMOTE_CODE=0 cd /opt/nim/llm/.venv/lib/python3.12/site-packages &&
  patch -p1 < /tmp/0001-harmony-utils-fix-assistant-channel.patch &&
  patch -p1 < /tmp/0002-serving-chat-improve-harmony-error-handling.patch &&
  rm /tmp/0001-harmony-utils-fix-assistant-channel.patch /tmp/0002-serving-chat-improve-harmony-error-handling.patch
10/14/2025 8:44 PM UTC
sha256:76177467018f7108ade41aa3ce74e9564b4a6164b44b5a08ebad551167490113COPY
docker/patches/0002-serving-chat-improve-harmony-error-handling.patch /tmp/
10/14/2025 8:44 PM UTC
sha256:138e74b1d668e3e06f3f7eb46ce8d9915d8d20a20cf760f165c107e34b5b8309COPY
docker/patches/0001-harmony-utils-fix-assistant-channel.patch /tmp/
10/14/2025 8:44 PM UTC
sha256:e16eb10a8957a1c461d1272fd8d0257aac71bc1c3482a0959e5395383acbcf03RUN
NIM_USER_ID=1000 NIM_MODEL_NAME=openai/gpt-oss-20b NIM_VERSION=1.12.4 NIM_NSPECT_ID=NSPECT-LJGD-9W15 NIM_MODEL_NSPECT_ID=NSPECT-SW5U-LCYW NIM_FORCE_TRUST_REMOTE_CODE=0 python3 /tmp/vllm-0.10.2-hf-hub-offline-fix.py &&
  rm /tmp/vllm-0.10.2-hf-hub-offline-fix.py
10/14/2025 8:44 PM UTC
sha256:4a4abf00f39ddeff08dc00be02189c56fa07cddc2d1638541be72b26de7bcddbCOPY
docker/vllm-0.10.2-hf-hub-offline-fix.py /tmp/vllm-0.10.2-hf-hub-offline-fix.py
10/14/2025 8:44 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.