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
nemo-rl
Container
NVIDIA
NVIDIA
nemo-rl

NVIDIA NeMo™ RL accelerates reinforcement learning post-training with high-performance GPU backends, offering scalable GRPO, DPO, SFT, and distillation for multimodal models from single-node experiments to enterprise-scale clusters.

LayerLabelCreated
1e23eaada379a709bdc17b45bab5e37c9cb7f80368831b801c744417533f9971CONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/nemo-rl
03/08/2026 2:41 AM UTC
98112ef76ff0b004ab70bcbd74f9e630626fb7ed15fcc5dd57940972e026867aRUN
UV_VERSION=0.9.7 PYTHON_VERSION=3.12 NEMO_GYM_PREFETCH_CONFIGS=examples/configs/grpo_superv3.yaml MAX_JOBS= NVTE_BUILD_THREADS_PER_JOB= BUILD_CUSTOM_VLLM=1 BUILD_CUSTOM_VLLM_URL=https://github.com/CentML/vllm.git BUILD_CUSTOM_VLLM_REF=nemotron-h-rl-2-mtp-fix-2 BUILD_CUSTOM_VLLM_PRECOMPILED_WHEEL_LOCATION=https://github.com/vllm-project/vllm/releases/download/v0.13.0/vllm-0.13.0-cp38-abi3-manylinux_2_31_x86_64.whl BUILD_CUSTOM_FLASHINFER= BUILD_CUSTOM_FLASHINFER_URL= BUILD_CUSTOM_FLASHINFER_REF= SKIP_VLLM_BUILD= SKIP_SGLANG_BUILD=1 CUSTOM_SETUP_FNAME=install_apptainer.sh NEMO_RL_COMMIT=956a394210ddd0b80c5233fe4d79938c080f019e NVIDIA_BUILD_ID=278388287 NVIDIA_BUILD_REF=4e087c4f5fcd2e4cf056f1937cafa335477af506 RC_DATE=0.5.0.super TARGETARCH=amd64 python tools/generate_fingerprint.py > /opt/nemo_rl_container_fingerprint
03/08/2026 2:41 AM UTC
7f69121b11e6baa839470cb2cb4dbb151eba7748c37bdcddf4a44ee8e1a7af21LABEL
com.nvidia.build.ref=4e087c4f5fcd2e4cf056f1937cafa335477af506
03/08/2026 2:41 AM UTC
1597ded063e91703151913e2a788329ba0ddaf2e39cd39e04af36d277b548d1cLABEL
com.nvidia.build.id=278388287
03/08/2026 2:41 AM UTC
ab75b9f1040498330c4c108f2fa70072884e617bb4e7810a31b1c522587c82f9ENV
NVIDIA_BUILD_REF=4e087c4f5fcd2e4cf056f1937cafa335477af506
03/08/2026 2:41 AM UTC
022a5c581657d2620f56034d7e93624232bb9debc3d6ee97370a985d87247e10ENV
NVIDIA_BUILD_ID=278388287
03/08/2026 2:41 AM UTC
9ace2e6bf8ed73a89b034765d2bb50396f767d1584339db8b7ad7befb86f5b18ENV
NEMO_RL_COMMIT=956a394210ddd0b80c5233fe4d79938c080f019e
03/08/2026 2:41 AM UTC
e5689030b27e196cee8ecedb0c7ebfc1b36d56ecc29e38fbb8bc52a1b0a69df2ARG
TARGETARCH=amd64
03/08/2026 2:41 AM UTC
85183e0426a4cd0367843c209937c7370d5570f25450e8ee18f0c21a0066b296ARG
RC_DATE=0.5.0.super
03/08/2026 2:41 AM UTC
af8aab3001ce0df7bc32f6be7be084d64714453b21aa2b6723df657109e583a1ARG
NVIDIA_BUILD_REF=4e087c4f5fcd2e4cf056f1937cafa335477af506
03/08/2026 2:41 AM 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.