PD Disaggregation VLLM Deployment on Alternative AI Accelerators Using Llm-d
Talkat KubeCon + CloudNativeCon + OpenInfra Summit + PyTorch Conference China 2026 · 2026-09-07..09-09·
summary
Covers deploying a Prefetch/Disaggregation (PD) variant of vLLM on alternative AI accelerators using llm-d. Describes integrating PD disaggregation and vLLM with llm-d to run on non-NVIDIA hardware, focusing on software components and deployment steps for those accelerators.
AI-written summary · about
related talks
27mServing PyTorch LLMs at Scale: Disaggregated Inference With Kubernetes and Llm-d
25mvLLM: Easy, Fast, and Cheap LLM Serving for Everyone
19mNo GPU Left Behind: Scaling Online LLM Training With...
32mScaling Generative AI Inference with llm-d
39mAccelerating Open-Source RL and Agentic Inference with vLLM
29mMulti-Accelerator PyTorch Serving With NxD Inference and vLLM
31mThe Evolution of Multi-GPU Inference in vLLM
20mSGLang: An Efficient Open-Source Framework for Large-Scale LLM Serving