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
    		10/07/2025 10:17 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    HF_HUB_CACHE=/app/cache
    		10/07/2025 10:17 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    MODEL_EXPRESS_CACHE_DIRECTORY=/app/cache
    		10/07/2025 10:17 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    MODEL_EXPRESS_DATABASE_PATH=/app/models.db
    		10/07/2025 10:17 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    MODEL_EXPRESS_LOGGING_LEVEL=info
    		10/07/2025 10:17 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    MODEL_EXPRESS_SERVER_PORT=8001
    		10/07/2025 10:17 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4EXPOSE
    [8001/tcp]
    		10/07/2025 10:17 PM UTC
    sha256:4eff2940159f2dc496d86b01bba95a7ff75b20be92b4e9b5af41769a799e3161COPY
    ATTRIBUTIONS_Rust.md .
    		10/07/2025 10:17 PM UTC
    sha256:5c98860ffccd5b0662f06575c8384572ba7c9d2d3e524e128896d7db0a42d7f0COPY
    /app/target/release/fallback_test .
    		10/07/2025 10:17 PM UTC
    sha256:5fa461994253d7c3161643cac84154fdd65c1f1fd30f07cb3a2a4696fe804126COPY
    /app/target/release/test_single_client .
    		10/07/2025 10:17 PM UTC