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
ModelExpress Server
Container
NVIDIA
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
06/10/2026 3:25 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
HF_HUB_CACHE=/app/cache
06/10/2026 3:25 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
MODEL_EXPRESS_CACHE_DIRECTORY=/app/cache
06/10/2026 3:25 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
MODEL_EXPRESS_LOG_LEVEL=info
06/10/2026 3:25 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
MODEL_EXPRESS_SERVER_PORT=8001
06/10/2026 3:25 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4EXPOSE
[8001/tcp]
06/10/2026 3:25 PM UTC
sha256:cee2f96c155ecaf0f0ef75ae154ebaf39490dff5c9ef0ec70af5ddb89b62f223COPY
NOTICES .
06/10/2026 3:25 PM UTC
sha256:46140142f976add25933005444e43bd798bdc420f84074230048e6d89eebdae4COPY
/app/target/release/fallback_test .
06/03/2026 1:10 AM UTC
sha256:2a44b8c3f9dbb1354420e4049a267822f1579e9b25476db9314653288c89839bCOPY
/app/target/release/test_client .
06/03/2026 1:10 AM UTC
sha256:4993e5fc626dc03ee06008759b2e00ece00a6cb03057b17e279af1110524754cCOPY
/app/target/release/modelexpress-cli .
06/03/2026 1:10 AM UTC