Skip to content

@ai-dynamo Dynamo

All

    Repositories list

    17 repositories

    • aisimulate

      Public
      AISimulate predicts LLM serving behavior and searches for strong deployment configurations offline, without bringing up a GPU serving cluster
      Python
      •
      Other
      •15•42•15•55•Updated Sep 25, 2026Sep 25, 2026

    • dynamo

      Public
      A Datacenter Scale Distributed Inference Serving Framework
      kubernetesrustrouting-engine
      kubernetesrustrouting-engineomnidiffusionvllmllm-inferencetensorrt-llmsglangdisaggregated-serving
      Rust
      •
      Other
      •1.6k•8.2k•429•1.1k•Updated Sep 25, 2026Sep 25, 2026

    • frontend-crates

      Public
      Rust
      •
      Apache License 2.0
      •37•22•7•37•Updated Sep 25, 2026Sep 25, 2026

    • velo

      Public
      Rust
      •
      Apache License 2.0
      •3•6•2•8•Updated Sep 24, 2026Sep 24, 2026

    • aitune

      Public
      NVIDIA AITune is an inference toolkit designed for tuning and deploying Deep Learning models with a focus on NVIDIA GPUs.
      deep-learninginferencetorch
      deep-learninginferencetorchnvidiatensorrtnvidia-gpuonnxruntimetorch-tensorrtai-dynamo
      Python
      •
      Apache License 2.0
      •33•283•0•5•Updated Sep 24, 2026Sep 24, 2026

    • snapshot

      Public
      Snapshot gets GPU pods ready in seconds instead of minutes — by restoring a fully initialized GPU worker instead of starting one from scratch. Kubernetes-native…
      kubernetesgpuinference
      kubernetesgpuinferencecold-startcriucheckpoint-restorecuda-checkpoint
      Go
      •
      Apache License 2.0
      •17•57•52•62•Updated Sep 24, 2026Sep 24, 2026

    • nixl

      Public
      NVIDIA Inference Xfer Library (NIXL)
      C++
      •
      Other
      •454•1.3k•67•217•Updated Sep 24, 2026Sep 24, 2026

    • aiperf

      Public
      AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.
      Python
      •
      Apache License 2.0
      •196•720•42•70•Updated Sep 24, 2026Sep 24, 2026

    • modelexpress

      Public
      Model Express is a Rust-based component meant to be placed next to existing model inference systems to speed up their startup times and improve overall performa…
      Python
      •
      Apache License 2.0
      •83•169•33•46•Updated Sep 24, 2026Sep 24, 2026

    • grove

      Public
      Kubernetes enhancements for Network Topology Aware Gang Scheduling & Autoscaling
      kubernetesgpuinference
      kubernetesgpuinferenceoperatorauto-scalingrole-basedgrovemultinodeauto-scaling-groupgang-scheduling
      Go
      •
      Apache License 2.0
      •89•270•44•41•Updated Sep 23, 2026Sep 23, 2026

    • kvcr

      Public
      Python
      •
      Apache License 2.0
      •14•43•2•5•Updated Sep 22, 2026Sep 22, 2026

    • aiconfigurator

      Public
      Offline optimization of your disaggregated Dynamo graph
      Python
      •
      Apache License 2.0
      •167•452•57•27•Updated Sep 18, 2026Sep 18, 2026

    • openengine

      Public
      OpenEngine is a vendor-neutral gRPC protocol for coordinating inference engines and distributed frameworks.
      Apache License 2.0
      •1•1•8•1•Updated Sep 16, 2026Sep 16, 2026

    • enhancements

      Public
      Enhancement Proposals and Architecture Decisions
      Apache License 2.0
      •19•11•4•60•Updated Sep 4, 2026Sep 4, 2026

    • .github

      Public
      3•1•0•0•Updated Sep 2, 2026Sep 2, 2026

    • flextensor

      Public
      FlexTensor is a tensor offloading and management library for PyTorch that enables running large models on limited GPU memory by intelligently offloading tensors…
      Python
      •
      Apache License 2.0
      •15•115•2•2•Updated Aug 18, 2026Aug 18, 2026

    • agent-plugins

      Public
      TypeScript
      •
      Apache License 2.0
      •4•6•0•2•Updated Jul 10, 2026Jul 10, 2026
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.