AI Blogs#
Beyond Embedding Quantization: Quark UINT4 Qwen3.8-Flash-Next on Ryzen AI Halo
Explore n-gram table choices for Qwen3.8-Flash-Next with AMD Quark UINT4, including accuracy and response-length tradeoffs.
AMD Life Science 26.08: A Complete Medical Imaging Stack on AMD Instinct™ GPUs
Explore the AMD Life Science 26.08 medical-imaging stack on AMD Instinct™ GPUs, from image I/O through inference to annotation.
Accelerating GLM-5.2 on AMD Instinct MI355X: EvalScope Benchmarks with Prefix Caching
Learn how to optimize GLM-5.2 FP8 long-context inference on AMD Instinct MI355X GPUs using prefix caching and end-to-end inference stack tuning.
Parallelism for Long-Context Serving: GLM-5.3-Flash on MI300X
Measured throughput of GLM-5.3-Flash on MI300X: how KV-cache capacity shapes TP8 and DP8+EP8 serving, with BF16 and FP8 KV cache.
Introducing the ROCm Handbooks
Discover the ROCm handbooks: book-style HTML and PDF guides that take you from your first HIP kernel to optimizing code for AMD GPUs.
MONAILabel 0.8.5 on AMD Instinct™ GPUs: Interactive Medical-Image Annotation
Learn how to run MONAILabel 0.8.5 for interactive medical-image annotation on AMD Instinct™ GPUs.
PrimusClaw: An Open-Source Managed Agent Runtime for AMD Instinct GPU Clusters
PrimusClaw is an open-source managed agent runtime that hosts durable, sandboxed agent sessions on your own AMD Instinct GPU clusters.
ROCm InferaSim: Cut LLM Serving Trial Costs and Deploy the Best Configuration
Learn how ROCm InferaSim predicts LLM serving performance on AMD Instinct GPUs from a few short runs, so you can deploy the best configuration.
From Operator to Kernel: Profile DeepSeek-V4-Flash in Primus with madengine
Profile an eight-layer training proxy derived from the DeepSeek-V4-Flash Primus configuration on eight MI350X GPUs with madengine and TraceLens, then turn operator-to-kernel insights into faster runs.
Online Quantization: Smooth Path from One Checkpoint to Any Desired Serving Scenario
Learn how AMD Quark's online quantization quantizes LLM weights at load time across vLLM, ATOM, and SGLang, with per-layer mixed FP8/MXFP4 recipes.
GLM-5.2 AgentX on AMD Instinct MI355X: Boosting Throughput and Interactivity
Learn how cache and kernel optimizations raised GLM-5.2 AgentX throughput and interactivity on AMD Instinct MI355X.
Quark Mixed-Precision Quantization for Wan2.2 Video Generation on AMD Instinct GPUs
Apply AMD Quark mixed-precision MXFP4 quantization to Wan2.2-T2V-A14B video generation with calibration-driven block selection.