Amazon SageMaker HyperPod now supports Disaggregated Prefill and Decode (DPD), an inference optimization that separates the two phases of large language model (LLM) inference — prefill and decode — onto dedicated GPU pools and transfers the key-value (KV) cache between them over Elastic Fabric Adapter (EFA) using GPU-Direct RDMA. Customers running LLMs in production for chat assistants, agentic pipelines, retrieval-augmented generation, and long-document analysis need consistent per-token latency and predictable throughput under mixed traffic, but when prefill and decode share the same GPU, a

Source: AWS What's New — read the full report at the original publisher.

This is a curated wire item. The Continuum Brief does not republish full third-party articles; this entry links to the original source.