At PyTorch Conference North America 2026, Nicolò Lucchesi, Research Engineer at @MistralAI and vLLM maintainer, will present joint work with @AWS and @RedHat on how disaggregated serving in vLLM has evolved to support the latest generation of hybrid models. This session will cover the evolution of disaggregated serving for modern hybrid architectures, protocol developments aimed at reducing end-to-end latency, and new key-value pinning mechanisms designed for reliability at scale. Join us in San Jose on October 20-21: #PyTorchCon# @vllm_project

Join Thomas Cottenier from @Arm at PyTorch Conference North America in San Jose this October 20-21. Thomas will present how AI agents can synthesize customized, target-specific runtimes using PyTorch components like torch.export, ExecuTorch, and torchao. This approach removes redundant prefill computation and creates streamlined inference pipelines that deliver high performance directly on edge hardware. Register now for PyTorch Conference North America: #PyTorchCon#

At PyTorch Conference North America, Ricardo Noriega de Soto, Tech Lead for the vLLM Omni team and Alexander Brooks, Principal Machine Learning Engineer @RedHat, will demonstrate how extending vLLM’s prefix caching mechanism to multistage pipelines boosts inference speeds while reducing GPU memory overhead. Join us in San Jose on October 20th to learn practical strategies for optimizing complex AI workloads: #PyTorchCon# @vllm_project

TRANSIT (TRANsparent Scale-In for multi-node Training) is a runtime that makes unified virtual memory practical for large-scale LLM training, enabling models to train on up to 50% fewer GPUs without requiring modification to existing PyTorch training code. Hyungyo Kim, Ph.D. Candidate in Electrical and Computer Engineering, University of Illinois at Urbana-Champaign will present on TRANSIT as a poster at PyTorch Conference North America with Apoorve Mohan from IBM Research. Learn how to train more with less at PyTorch Conference North America: