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
    ModelExpress Server
    Container
    NVIDIA
    ModelExpress Server

    Model Express is a Rust-based model cache management service designed to be deployed as a sidecar alongside existing inference solutions such as NVIDIA Dynamo.

  • LayerLabelCreated
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4CMD
    ./modelexpress-server
    		07/31/2026 1:10 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    HF_HUB_CACHE=/app/cache
    		07/31/2026 1:10 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    MODEL_EXPRESS_CACHE_DIRECTORY=/app/cache
    		07/31/2026 1:10 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    MODEL_EXPRESS_LOG_LEVEL=info
    		07/31/2026 1:10 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    MODEL_EXPRESS_SERVER_PORT=8001
    		07/31/2026 1:10 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4EXPOSE
    [8001/tcp]
    		07/31/2026 1:10 AM UTC
    sha256:498a748596aaf7600bc4717749077ca36fe8ee3bfaefe4ad3f16306b443fcd5eCOPY
    NOTICES .
    		07/31/2026 1:10 AM UTC
    sha256:c428b3e1405dc2c3be8a156a53baf9aafe292a18fa87a51c6d33a14863d322faCOPY
    /app/target/release/fallback_test .
    		07/31/2026 1:10 AM UTC
    sha256:148a0527c343514302a582628befcb9313eac80ec00d1a31cbadc0bba3388df6COPY
    /app/target/release/test_client .
    		07/31/2026 1:10 AM UTC
    sha256:b3fea2e793da1929e055ce47d2e2e7ac01fcbcd05d17e3251817a563ee050fcaCOPY
    /app/target/release/modelexpress-cli .
    		07/31/2026 1:10 AM UTC