https://www.infoq.com InfoQ GPU feed https://www.infoq.com/presentations/llm-inference-kv-cache/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=GPU <img src="https://res.infoq.com/presentations/llm-inference-kv-cache/en/mediumimage/medium-1792066105733.jpeg"/><p>Khawaja Shams shares a distributed systems perspective on scaling LLM inference stacks efficiently. He discusses practical strategies for optimizing GPU utilization, managing KV cache memory cliffs, leveraging tiered storage, reducing tail latency, and implementing disaggregated prefill and decode architectures to improve overall fleet performance, cost economics, and availability.</p> <i>By Khawaja Shams</i> Optimization QCon AI Boston 2026 Large language models Redis Caching Valkey Transcripts GPU Distributed Systems AI, ML & Data Engineering Development Architecture & Design presentation Tue, 27 Oct 2026 11:00:00 GMT https://www.infoq.com/presentations/llm-inference-kv-cache/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=GPU Khawaja Shams 2026-10-27T11:00:00Z /presentations/llm-inference-kv-cache/en https://www.infoq.com/news/2026/10/tornadovm-7-gpu/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=GPU <img src="https://www.infoq.com/styles/static/images/logo/logo_bigger.jpg"/><p>TornadoVM, an open-source heterogeneous programming framework for Java, has reached version 7.0. It automatically accelerates Java programs on multi-core CPUs and GPUs and provides a rich GPU programming ecosystem in Java that can be used with any mainstream JDK distribution e.g. Temurin, Red Hat OpenJDK, Coretto, Oracle, GraalVM or Zulu.</p> <i>By Ben Evans</i> Llama3 Java GPU AI, ML & Data Engineering Development Architecture & Design news Wed, 21 Oct 2026 03:00:00 GMT https://www.infoq.com/news/2026/10/tornadovm-7-gpu/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=GPU Ben Evans 2026-10-21T03:00:00Z /news/2026/10/tornadovm-7-gpu/en