Skip to main content

Building GPU Kernels in Python with ROCm FlyDSL

abstract background

This advanced hands-on workshop introduces ROCm FlyDSL, a Python-based domain-specific language (DSL) for developing GPU kernels with low-level control on AMD GPUs. Attendees will receive a concise introduction to FlyDSL and learn how to implement GPU kernels in pure Python using the library. The workshop will also showcase how FlyDSL is used in production to improve end-to-end serving performance of Large Language Models like Kimi K2.5.

July 23, 2026 3:00 PM - 3:45 PM PDT

Christian Gilli
Christian Gilli

SMTS Product Application Engineer | AMD

Topic

Developer Platforms & Open Ecosystems

Session Type

Workshop

Related Product

Instinct, EPYC, ROCm

Related Sessions

View All Sessions
  • Accelerating LLM Inference on AMD GPUs with AMD ATOM

    This advanced hands-on workshop introduces AMD ATOM, an open-source optimized LLM inference backend for ROCm. Learn to serve LLMs with popular workflows using AMD-optimized attention & inference kernels. The Workshop introduces out-of-tree plugins for existing vLLM & SGLang users & aims at demonstrating how ATOM preserves familiarity of the frameworks while accelerating model execution & boosting inference performance, bridging opensource frameworks with the AMD high-performance inference stack.;This advanced hands-on workshop introduces AMD ATOM, an open-source optimized LLM inference backend for ROCm. Learn to serve LLMs with popular workflows using AMD-optimized attention & inference kernels. The Workshop introduces out-of-tree plugins for existing vLLM & SGLang users & aims at demonstrating how ATOM preserves familiarity of the frameworks while accelerating model execution & boosting inference performance, bridging opensource frameworks with the AMD high-performance inference stack.

    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. SOTA pre and post training performance with Primus, proven at scales of thousands of GPUs, positions an AMD Instinct GPU 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. SOTA pre and post training performance with Primus, proven at scales of thousands of GPUs, positions an AMD Instinct GPU as a competitive solution for model development at frontier labs, enterprises, and AI startups.

    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

  • 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

  • Inference Performance Tuning with AI Agents

    In this advanced user hands-on workshop learn all about AMD Agentic kernel development workflow and how to deploy it for your use case. This course will help replace weeks-long performance engineering with an Agentic self-directing loop that profiles, plans, optimizes, validates, and delivers production-ready kernel improvements automatically.;In this advanced user hands-on workshop learn all about AMD Agentic kernel development workflow and how to deploy it for your use case. This course will help replace weeks-long performance engineering with an Agentic self-directing loop that profiles, plans, optimizes, validates, and delivers production-ready kernel improvements automatically.

    July 23, 2026

  • ROCm Certification Associate: Architecture, Programming, and Optimization

    This 4-hour ROCm Certification workshop includes three hours of hands-on training followed by a one-hour certification exam. Participants will learn ROCm fundamentals, AMD GPU architecture, AI and HPC development, PyTorch, HIP programming, ROCm libraries, CUDA porting, profiling, and performance optimization. Guided labs provide practical experience building, debugging, and optimizing GPU-accelerated applications on AMD platforms.;This 4-hour ROCm Certification workshop includes three hours of hands-on training followed by a one-hour certification exam. Participants will learn ROCm fundamentals, AMD GPU architecture, AI and HPC development, PyTorch, HIP programming, ROCm libraries, CUDA porting, profiling, and performance optimization. Guided labs provide practical experience building, debugging, and optimizing GPU-accelerated applications on AMD platforms.

    July 23, 2026

  • Evolving Comms Libraries in ROCm for Future AI Workloads

    This talk covers advances in AMD ROCm communication libraries for large-scale AI. RCCL innovations include copy-engine offloading, symmetric memory, GPU-initiated collectives, congestion-aware load balancing, and port failover. rocSHMEM extends an OpenSHMEM-like model with Python and Triton support, while NIXL contributions enable efficient inference. Together, they support diverse NICs like AMD Pensando AINICs and Broadcom Thor.;This talk covers advances in AMD ROCm communication libraries for large-scale AI. RCCL innovations include copy-engine offloading, symmetric memory, GPU-initiated collectives, congestion-aware load balancing, and port failover. rocSHMEM extends an OpenSHMEM-like model with Python and Triton support, while NIXL contributions enable efficient inference. Together, they support diverse NICs like AMD Pensando AINICs and Broadcom Thor.

    July 22, 2026