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
SGLang Model-Free NIM
Container
NVIDIA
NVIDIA
SGLang Model-Free NIM

SGLang Model-Free NIM container.

NVIDIA NIM
LayerLabelCreated
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
/opt/nim/start_server.sh
07/16/2026 6:02 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
nvs:1000
07/16/2026 6:02 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1WORKDIR
/opt/nim
07/16/2026 6:02 PM UTC
sha256:3f6d1bec39b3cd55a9b2db24b2d41e64ceb630268ec551f2712ce7ba51aa1d9aRUN
/bin/bash -lc chmod 0755 /opt/nim/start_server.sh
07/16/2026 6:02 PM UTC
sha256:4da22d95d8685ff90ebaa8f449f4f8c9138236043529722cacffa7827569b14aCOPY
docker/start_server.sh /opt/nim/start_server.sh
07/16/2026 6:02 PM UTC
sha256:83c573c9a624323fd9373ad912c8d6e8e5dde2a7a6317434de045502f8cd41b1COPY
docker/overlays/lowest_tp_selector.py /usr/local/lib/python3.12/dist-packages/nim_stack/cutomize_profile_secltion/lowest_tp_selector.py
07/16/2026 6:02 PM UTC
sha256:ecf87c564629a3cd058a0b00a451659e95191a350cce0b361198a1fbc4b9b954COPY
docker/overlays/lowest_tp_selector.py /opt/nim/cutomize_profile_secltion/lowest_tp_selector.py
07/16/2026 6:02 PM UTC
sha256:7ed3e9b1461f4e046100ea72deed0aa3c037a9ac808df2ec7fac83c4b9fd1abcCOPY
VERSION /opt/nim/VERSION
07/16/2026 6:02 PM UTC
sha256:3e109c8c5f4e69c5592ef16efd4c1abfe2337c8aff09e3c02bac7d7d6b31ead8RUN
/bin/bash -lc set -euo pipefail; patch_root=/opt/nim/patches/027_m3_tp8_prefill_guard; source_root=/sgl-workspace/sglang; cd "${source_root}"; patch --batch --forward --fuzz=0 --dry-run -p1 < "${patch_root}/patch.diff"; patch --batch --forward --fuzz=0 -p1 < "${patch_root}/patch.diff"; python3 -m py_compile python/sglang/srt/server_args.py; rm -rf "${patch_root}"
07/16/2026 6:02 PM UTC
sha256:295ff48acebd649c927159ee10020614541c21c3fa68c2d904af8d89508f55c1COPY
docker/patches/027_minimax-m3-mxfp8-tp8-prefill-graph/patch.diff /opt/nim/patches/027_m3_tp8_prefill_guard/patch.diff
07/16/2026 6:02 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.