AMD released version 2.2 of its enterprise AI reference stack, introducing multi-accelerator support for AMD Inference Microservices (AIMs) and AMD Solution Blueprints across AMD Instinct GPUs (MI300X…
AMD published a blog post detailing a workflow that combined ROCm profiling tools with Cursor's AI code-assist agent to optimize a double-precision HIP kernel on an Instinct MI250 GPU, achieving a cum…
AMD introduced an agentic RAG system called Enterprise Research Analyst that uses hipVS GPU-accelerated vector search as its retrieval backbone, demonstrating a multi-step pipeline that decomposes com…
AMD released ROCm 7.14, marking the production debut of TheRock, its new automated open-source build and release system for the ROCm software stack. The release expands hardware support to AMD Instinc…
AMD announced that with ROCm 7.2.1, users can now run PyTorch and ComfyUI natively on Windows on an AMD Ryzen AI Max+ processor, driving the integrated AMD Radeon 8060S GPU directly. The unified memor…
AMD has released a Triton-based optimization for video sparse attention on its ROCm platform, targeting Diffusion Transformers (DiTs) used in video generation. The implementation reduces the quadratic…
AMD's open-source GEAK agent-driven framework automated the optimization of the DeepSeekV4 MLA kernel, achieving a 2.10x improvement in end-to-end throughput and a 3.71x reduction in time-to-first-tok…
AMD's QuickReduce library now supports INT3 quantization for all-reduce communication in multi-GPU LLM inference, achieving a 22% reduction in on-wire data volume compared to INT4 on AMD Instinct MI35…
AMD has integrated an NVFP4 emulation pipeline into vLLM that enables AMD Instinct MI355 accelerators to serve standard NVFP4 quantized checkpoints directly, dequantizing weights to BF16 on-the-fly at…
AMD GPUs running SGLang Diffusion on ROCm achieve 1.5x to 6.3x speedups over Hugging Face Diffusers for image generation and editing tasks, as demonstrated on models including FLUX.1-dev, Qwen-Image, …
AMD has published an analysis of network traffic patterns in AI training clusters, identifying congestion hotspots and harmonic-like oscillations caused by synchronized collective communication operat…
AMD introduced SGLang-ATOM, a bridge connecting the SGLang serving framework with ATOM's ROCm-native execution path to accelerate large language model inference on AMD Instinct GPUs. The integration u…
AMD Silo AI and the Autoware Foundation are using GPU partitioning on AMD Instinct MI300X accelerators to accelerate hyperparameter optimization for autonomous driving perception models, enabling up t…
AMD contributed a compatibility update to JAX-Triton that supports most Triton features, enabling users to run virtually any Triton or Gluon kernel inside JAX with minimal changes. The update includes…
AMD Quark, a quantization library optimized for AMD Instinct MI350 GPUs, enables MXFP4 quantization for Diffusers and xDiT FLUX.1-dev image generation, achieving up to 1.92× speedup over BF16 eager an…
AMD has released the Primus Tuning Agent, a tool that automatically searches for optimal training configurations for large language models by using a projection engine as a fast scoring oracle. In a c…
AMD released AgentKernelArena, an open-source benchmarking framework for AI coding agents on GPU kernel optimization tasks using AMD Instinct GPUs. In tests on a 44-task subset, AMD's GEAKv3 agent ach…
AMD published a guide demonstrating a GPU-resident YOLO26 object detection pipeline on the Radeon AI PRO R9700 GPU using ROCm 7.2. The pipeline keeps video frames in VRAM from decode to bounding boxes…
AMD announced the acceleration of large-scale LLM inference on its Instinct MI350X/MI355X GPUs using Eagle3 speculative decoding and AMD Quark quantization. The work enables lossless inference speedup…
AMD announced a new kernel family, LDS-Pipelined Split-K GEMM, that accelerates LLM inference on AMD GPUs by optimizing decode-time GEMMs with small M and large N/K dimensions. The technique achieves …