# ModelExpress: Distributing Model Artifacts at the Speed of Light ModelExpress significantly reduces the transfer time of model weights. - **Source:** [Nvidia Developer Blog](https://developer.nvidia.com/blog) - **Published:** 2026-07-24 - **Topic:** [Data & AI](https://brifing.si/c/data-ai) - **Original article:** - **On Brifing:** https://brifing.si/s/758884ed-011f-4001-902c-84f76f4713a0 ## The Cost of Transferring Model Weights As model checkpoints grow to hundreds of gigabytes or even terabytes, the cost of transferring these weights increases rapidly. Moving these weights within a cluster has become a frequent operation. ## The Core Idea of ModelExpress ModelExpress introduces an approach that queries where compatible weights are located before loading a model. This ensures that each replica is not treated as an independent cold start but rather selects the fastest source and transfer path. ## Direct GPU-to-GPU Transfer If a serving peer already holds compatible weights in GPU, ModelExpress transfers them directly from GPU to GPU over P2P RDMA. This eliminates redundant storage accesses. ## Fast Startup Time ModelExpress transfers DeepSeek-V4 Pro weights and JIT Kernel cache artifacts from a serving replica into a fresh replica in under 10 seconds, reducing the total startup time from 8 minutes to 1 minute 44 seconds. ## Streaming from Remote Storage to GPU ModelExpress streams checkpoints from remote storage directly to GPU, eliminating intermediate downloads and reloads on local disk. This significantly speeds up the data transfer process. ## Multithreaded Tensor Reading Model Streamer uses a multithreaded tensor reader to fetch tensor ranges concurrently and place them in GPU. This keeps storage, network, and GPU copy paths continuously busy. ## Cluster Ingress: Single Download ModelExpress ensures that a shared disk cache layer in the cluster is populated only once. This prevents the same data from being downloaded multiple times. ## Direct Access from Local Storage to GPU In systems supporting GPUDirect Storage (GDS), ModelExpress reads checkpoints directly from local storage into GPU memory. This bypasses the intermediate copy required by conventional loaders. ## Local Reading with ModelStreamer ModelExpress can also load local checkpoints through ModelStreamer. This overlaps disk I/O with GPU placement, providing a fast path when direct storage-to-GPU access is unavailable. ## Weight Transfer from Serving Peer A key feature of ModelExpress is that if a replica is already serving the same model, the weights have mostly completed their journey. This replica is used as a live weight source. ## Conclusion and Importance ModelExpress significantly accelerates the transfer process of model weights, enhancing the efficiency of machine learning workflows. This is particularly advantageous in scenarios involving large models. ## Sources covering this story - https://developer.nvidia.com/blog/modelexpress-distributing-model-artifacts-at-the-speed-of-light/ — --- _Summary written by Brifing from the original reporting. Copyright in the original article belongs to its publisher; read the full piece at the link above._