Recent Posts#
Nitro-P: Pixel-Space Text-to-Image via Hierarchical Semantic-to-Pixel Generation
Nitro-P is an E-MMDiT-based pixel-space text-to-image model. It uses lower FLOPs while delivering evaluation metrics and visual quality comparable to latent-space text-to-image models.
FlashInfer on ROCm 10.1: The FlashInfer API with Automatic Kernel Routing
Explore the new attention and fused ops in FlashInfer on ROCm: the upstream API, with each call routed to optimized AITER or in-tree HIP kernels.
From a Text Prompt to a Playable 3D World: World Models, LLM NPCs, and RL on AMD Radeon™ Graphics
Turn a text prompt into a playable 3D world on one AMD Radeon graphics card with ROCm software: a video world model, Gaussian splats, LLM-driven NPCs and an RL agent.
ROCm 10.2.0: Advancing Performance, Stability, and Developer Experience
Explore ROCm 10.2.0, featuring refreshed frameworks, enhanced memory and library capabilities, and more as AMD advances the developer experience
An AITER Pin Keyed by Kernel Text: Faster Glue Than the Inductor Default
Learn how an AITER pin keyed by kernel text beats Inductor's default glue config, and how it compares with open-list autotune.
Keep the Agent Warm: How ATOM Serves AgentX Workloads on AMD Instinct MI355X GPUs
Learn how ATOM keeps AgentX coding sessions warm on AMD Instinct™ MI355X GPUs, from prefix and state reuse to prefill scheduling and fused decode kernels, using Kimi-K3.
Reproducing AMD MLPerf Training v6.1 Submission Result
Learn how to reproduce AMD's MLPerf Training v6.1 submission result.
Technical Deep Dive into AMD MLPerf Training v6.1 Results
In this blog, we share the technical details of how we accomplish the results in our MLPerf Training v6.1 submission.
GPU-Initiated DMA Copy Engines in RCCL and rocSHMEM
Learn how GPU-initiated SDMA engines in RCCL and rocSHMEM offload data transfers to free compute units and maximize scale-up bandwidth.
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.