InfoQ - GPU - Presentations https://www.infoq.com InfoQ GPU Presentations feed Presentation: Serving LLMs at Scale: The Hidden KV Cache Advantage https://www.infoq.com/presentations/llm-inference-kv-cache/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=GPU-presentations <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> Large language models Optimization Distributed Systems Transcripts Valkey Redis Caching GPU QCon AI Boston 2026 AI, ML & Data Engineering Architecture & Design Development 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-presentations Khawaja Shams 2026-10-27T11:00:00Z /presentations/llm-inference-kv-cache/en