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
    nemo-rl
    Container
    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
    sha256:62c4fa3b1572d944468e2f6e4f469ae025e08e914aadbea811be4c6a8104ff81RUN
    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_aarch64.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=278388288 NVIDIA_BUILD_REF=4e087c4f5fcd2e4cf056f1937cafa335477af506 RC_DATE=0.5.0.super TARGETARCH=arm64 echo "This distribution includes open source which is archived at the following URL: https://opensource.nvidia.com/oss/teams/nvidia/nemo-rl/${RC_DATE}:linux-${TARGETARCH}/index.html" > NOTICES.txt &&
  echo "For further inquiries or assistance, contact us at oss-requests@nvidia.com" >> NOTICES.txt
    		03/08/2026 2:47 AM UTC
    sha256:ecd07c99b7a9287d520e34dac450b9c12ecafc487f7afaaa50f87857dd495c5dRUN
    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_aarch64.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=278388288 NVIDIA_BUILD_REF=4e087c4f5fcd2e4cf056f1937cafa335477af506 RC_DATE=0.5.0.super TARGETARCH=arm64 python tools/generate_fingerprint.py > /opt/nemo_rl_container_fingerprint
    		03/08/2026 2:47 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
    com.nvidia.build.ref=4e087c4f5fcd2e4cf056f1937cafa335477af506
    		03/08/2026 2:47 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
    com.nvidia.build.id=278388288
    		03/08/2026 2:47 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    NVIDIA_BUILD_REF=4e087c4f5fcd2e4cf056f1937cafa335477af506
    		03/08/2026 2:47 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    NVIDIA_BUILD_ID=278388288
    		03/08/2026 2:47 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    NEMO_RL_COMMIT=956a394210ddd0b80c5233fe4d79938c080f019e
    		03/08/2026 2:47 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    TARGETARCH=arm64
    		03/08/2026 2:47 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    RC_DATE=0.5.0.super
    		03/08/2026 2:47 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    NVIDIA_BUILD_REF=4e087c4f5fcd2e4cf056f1937cafa335477af506
    		03/08/2026 2:47 AM UTC
    ...