NVIDIA Dynamo Snapshot: Fast Startup for Inference Workloads on Kubernetes | NVIDIA Technical Blog
… We are currently working on integrating the following features: GMS restore path with pluggable backends GDS, UCX, etc , currently gated on pending CUDA driver patch TensorRT-LLM support Multi-GPU and multi-node support via quiesce/resume hooks for PyTorch, NCCL, NIXL, etc. …