Skip to main content

Efficient LLM Serving at Scale with Unified Caching

abstract background

This is an advanced user hands-on workshop to show TensorMesh and AMD enabling efficient LLM serving through an unified caching layer. You will learn how tiered KV cache management can brings out the benefits of cache-aware inference, improving throughput under interactive latency SLAs, reducing TTFT through KV cache reuse/offload & enabling production-style distributed inference on Instinct GPUs.

July 23, 2026 13:00 - 13:45

Chun Fang
Chun Fang

SMTS Software Development Engineer | AMD

Haichen Zhang
Haichen Zhang

SMTS Product Application Engineer | AMD

Topic

AI Training & Inference

Session Type

Workshop

Related Product

Instinct, EPYC, ROCm

Related Sessions

View All Sessions
  • Beyond Generic AI: Building Domain-Specific Models at Enterprise Scale

    DProtein structure prediction is foundational to modern biology, enabling breakthroughs in drug discovery, enzyme engineering, and AI-driven science. We present ElMerFold, a production-scale synthetic data generation workflow running on the El Capitan system at 11,000 nodes and 44,000 APUs. ElMerFold processes ~41 million proteins at 2,378 structures/s, achieving a 16.3× improvement over prior approaches and reaching 969 PFLOP/s FP32 inference performance.;DProtein structure prediction is foundational to modern biology, enabling breakthroughs in drug discovery, enzyme engineering, and AI-driven science. We present ElMerFold, a production-scale synthetic data generation workflow running on the El Capitan system at 11,000 nodes and 44,000 APUs. ElMerFold processes ~41 million proteins at 2,378 structures/s, achieving a 16.3× improvement over prior approaches and reaching 969 PFLOP/s FP32 inference performance.

    July 23, 2026

  • Training at Scale with AMD Primus

    Primus makes large scale training on Instinct reliable, debuggable and highly performant. It supports the latest OSS training frameworks, models, and is expanding support to new, cutting-edge model architectures, training techniques, and datatypes. Primus’ SOTA pre and post training performance, proven at scales of thousands of GPUs, positions instinct as a competitive solution for model development at frontier labs, enterprises and AI startups.;Primus makes large scale training on Instinct reliable, debuggable and highly performant. It supports the latest OSS training frameworks, models, and is expanding support to new, cutting-edge model architectures, training techniques, and datatypes. Primus’ SOTA pre and post training performance, proven at scales of thousands of GPUs, positions instinct as a competitive solution for model development at frontier labs, enterprises and AI startups.

    July 23, 2026

  • Benchmarking AI Systems: from Model Metrics to Real-World Performance

    The agentic AI stack has evolved to fast multi-model orchestration, tool-augmented reasoning, and long-running inference chains. The hardware conversation hasn't kept up, and many teams default to one GPU vendor without evaluating alternatives. This interactive session is for builders to learn what they're missing. We'll review head-to-head benchmark data from third-party testing, discuss production-ready serving stacks on ROCm, and break down TCO for teams running multi-step agents at scale.;The agentic AI stack has evolved to fast multi-model orchestration, tool-augmented reasoning, and long-running inference chains. The hardware conversation hasn't kept up, and many teams default to one GPU vendor without evaluating alternatives. This interactive session is for builders to learn what they're missing. We'll review head-to-head benchmark data from third-party testing, discuss production-ready serving stacks on ROCm, and break down TCO for teams running multi-step agents at scale.

    July 23, 2026

  • Agentic Kernel Performance Tuning with AMD ROCm

    This session introduces an agentic kernel development workflow for optimizing AI and HPC workloads on AMD ROCm. Learn how a self-directing optimization loop can profile, analyze, optimize, validate, and generate production-ready kernel improvements with minimal manual tuning. The talk highlights how AMD is accelerating kernel engineering by reducing weeks of performance optimization effort into an automated, scalable workflow for developers and performance engineers.;This session introduces an agentic kernel development workflow for optimizing AI and HPC workloads on AMD ROCm. Learn how a self-directing optimization loop can profile, analyze, optimize, validate, and generate production-ready kernel improvements with minimal manual tuning. The talk highlights how AMD is accelerating kernel engineering by reducing weeks of performance optimization effort into an automated, scalable workflow for developers and performance engineers.

    July 23, 2026

  • Power is Your Biggest Hidden Cost: How AMD Can Help

    Power is the AI infrastructure cost nobody budgets for until it breaks the business case. In this interactive technical session, an expert from 5C joins AMD to unpack how power consumption impacts total cost of ownership across inference and training deployments. Discuss how intelligent power management, real-world thermal constraints, and silicon-level efficiency shape what your AI infrastructure can sustain. Practical insight for architects and operators making deployment decisions today.;Power is the AI infrastructure cost nobody budgets for until it breaks the business case. In this interactive technical session, an expert from 5C joins AMD to unpack how power consumption impacts total cost of ownership across inference and training deployments. Discuss how intelligent power management, real-world thermal constraints, and silicon-level efficiency shape what your AI infrastructure can sustain. Practical insight for architects and operators making deployment decisions today.

    July 23, 2026

  • Accelerating LLM Inference on AMD ROCm with AITER and ATOM

    This technical talk introduces AITER and ATOM, optimized inference technologies for AMD ROCm software. Learn how AITER accelerates LLM and MoE execution with optimized kernels and distributed inference enhancements, while ATOM integrates these capabilities into familiar vLLM and SGLang workflows through plugin-based acceleration. The session highlights how AMD enables scalable, high-performance open-source LLM serving while preserving existing developer and deployment workflows.;This technical talk introduces AITER and ATOM, optimized inference technologies for AMD ROCm software. Learn how AITER accelerates LLM and MoE execution with optimized kernels and distributed inference enhancements, while ATOM integrates these capabilities into familiar vLLM and SGLang workflows through plugin-based acceleration. The session highlights how AMD enables scalable, high-performance open-source LLM serving while preserving existing developer and deployment workflows.

    July 23, 2026

  • Transformation of AMD ROCm Software in a New AI Era

    This session explores an AI-native GPU software stack for large-scale AI systems on AMD hardware. Learn how AI-assisted GPU programming, distributed training, optimized inference, memory expansion, and agentic deployment workflows are enabling scalable AI infrastructure across clusters and hyperscale environments. The talk highlights practical approaches for improving performance, observability, automation, and resource efficiency on the AMD GPU platforms.;This session explores an AI-native GPU software stack for large-scale AI systems on AMD hardware. Learn how AI-assisted GPU programming, distributed training, optimized inference, memory expansion, and agentic deployment workflows are enabling scalable AI infrastructure across clusters and hyperscale environments. The talk highlights practical approaches for improving performance, observability, automation, and resource efficiency on the AMD GPU platforms.

    July 23, 2026

  • Build Your Openclaw Agent with Multi-Modal Models

    This is a beginner level hands-on class which will show you how to build your own Openclaw agent using opensource multi-modal models. This course will also show you how to set up an opensource model server with vLLM/SGLang and connect your agent to it.;This is a beginner level hands-on class which will show you how to build your own Openclaw agent using opensource multi-modal models. This course will also show you how to set up an opensource model server with vLLM/SGLang and connect your agent to it.

    July 23, 2026