… July 23, 2026 Accelerating vLLM Inference on AMD Instinct GPUs with AMD ATOM This advanced hands-on workshop introduces AMD ATOM an opensource optimized LLM inference backend for ROCm. Learn to serve LLMs with popular workflows using AMD-optimized attention & inference kernels. …
… July 23, 2026 Accelerating vLLM Inference on AMD Instinct GPUs with AMD ATOM This advanced hands-on workshop introduces AMD ATOM an opensource optimized LLM inference backend for ROCm. Learn to serve LLMs with popular workflows using AMD-optimized attention & inference kernels. …
… Video generation, image generation, 3D generation, music generation, and local LLM inference all depend on frameworks, drivers, libraries, and workflow tools working together. When that stack is incomplete, the experience breaks. When it is optimized, local AI becomes practical. …
… Download the vllm docker image and clone the MAD repo. docker pull rocm/vllm:rocm6.2 mi300 ubuntu20.04 py3.9 vllm 0.6.4 git clone https://github.com/ROCm/MAD cd MAD pip install -r requirements.txt Launch a benchmark program. export MAD SECRETS HFTOKEN="your personal Hugging Face token to access gat… …
… New LLM Model Support DeepSeek-R1 Distill Series: Llama-8B, Qwen-1.5B, Qwen-7B Qwen2 Series: Qwen2-1.5B, Qwen2-7B Gemma2-2B AMD-OLMO-1B-SFT-DPO Codellama-7B, Mistral-7B and more Full Release Notes Technical Resources GAIA: An Open-Source Project from AMD for Running Local LLMs on Ryzen™ AI Introduc… …
… Hear how organizations build training pipelines and deliver production inference on Vultr using AMD Instinct GPUs and ROCm, with attention to data locality, secure networking, Kubernetes orchestration, benchmarking, cost controls, and scale-out operations. …
… The Ryzen AI Halo developer platform works with the frameworks and tools developers already use – PyTorch, vLLM, llama.cpp, Ollama, ComfyUI and LM Studio – and is optimized for AMD ROCm™ software, supporting large language models, diffusion models and agent workflows locally on a single system. …
… July 23, 2026 Efficient LLM Serving at Scale with Unified Caching This is an advanced user hands-on workshop to show TensorMesh and AMD enabling efficient LLM serving through an unified caching layer. …