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
    		11/28/2025 1:29 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    HF_HUB_CACHE=/app/cache
    		11/28/2025 1:29 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    MODEL_EXPRESS_CACHE_DIRECTORY=/app/cache
    		11/28/2025 1:29 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    MODEL_EXPRESS_DATABASE_PATH=/app/models.db
    		11/28/2025 1:29 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    MODEL_EXPRESS_LOGGING_LEVEL=info
    		11/28/2025 1:29 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    MODEL_EXPRESS_SERVER_PORT=8001
    		11/28/2025 1:29 AM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4EXPOSE
    [8001/tcp]
    		11/28/2025 1:29 AM UTC
    sha256:0673ee06dcba5376813ae5f1b99c70c41323cf55b250a0c456a0d9e46997f173COPY
    ATTRIBUTIONS_Rust.md .
    		11/28/2025 1:29 AM UTC
    sha256:3a328104e013baf9b95c3179d567033d331d744006c478ee167c0881e56427afCOPY
    /app/target/release/fallback_test .
    		11/28/2025 1:29 AM UTC
    sha256:37901853648ba802d19d2bc5020e63ee8dca737925c76cd60a127a23747cee56COPY
    /app/target/release/test_single_client .
    		11/28/2025 1:29 AM UTC