Performance Results with AMD ROCm™ Software
…on AMD Instinct™ GPUs running popular AI models. The results found on this page highlight both Inference and Training benchmarks. The results are organized by the following: AI Inference : vLLM, xDiT AI…
Search
Top stories
Maincode Builds An AI Factory for Australia with AMD
…This system-level evaluation differs from traditional HPC benchmarking. They ran what Lemphers calls an exploded modeling exercise across accelerators, nodes and rack design, power, cooling, networking, and support. “It is all…
LLM-D Serving for AMD Instinct GPUs on OCI
…ONNX Model Serving with Triton Inference Server on AMD GPUs — ROCm Blogs Step-by-step guide to building, deploying, and benchmarking ONNX models with Triton Inference Server and MIGraphX on AMD GPUs…
vLLM in 2026: challenges and Optimizations
…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…
Agentic Kernel Performance Tuning with AMD ROCm
…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…
Accelerating LLM Inference on AMD ROCm with AITER and ATOM
…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…
Transformation of AMD ROCm Software in a New AI Era
…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…
AMD Versal Prime Series Adaptive SoCs
…Vitis Model Composer Vitis™ Model Composer is a model-based design tool that enables rapid design exploration within the MathWorks MATLAB® and Simulink® environment and accelerates the path to production on AMD…
Efficient LLM Serving at Scale with Unified Caching
…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…
Building Hybrid Multi-Agent Systems from Client to Cloud
…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…