Accelerating FastVideo on AMD GPUs with TeaCache — ROCm Blogs
Enabling ROCm support for FastVideo inference using TeaCache on AMD Instinct GPUs, accelerating video generation with optimized backends| ROCm Blogs
LLM inference pipelines are hitting a scalability wall as prefill and decode phases compete for the same compute, causing latency spikes and underutilized resources. DistServe tackles this by disaggregating prefill and decode computation across separate GPUs—eliminating interference, decoupling resource planning, and unlocking new levels of optimization for both time-to-first-token (TTFT) and time-per-output-token (TPOT).| AMD ROCm Blogs
Advancements in large-scale language models (LLMs) have led to significant performance breakthroughs across various domains, especially in natural language processing. LLMs typically consist of billions of parameters, resulting in substantial computational, storage, and deployment challenges. Inter-GPU communication overhead often emerges as a key bottleneck limiting overall system performance. In tensor-parallel setups, every layer requires frequent all-reduce operations—synchronizing larg...| AMD ROCm Blogs
For developers pushing LLM inference to its limits, efficiency and speed are non-negotiable. DeepSeek-V3’s Multi-head Latent Attention (MLA) layer rethinks traditional attention to cut memory bandwidth pressure while maintaining accuracy. Combined with the matrix absorbed optimization and AMD’s AI Tensor Engine for ROCm (AITER), this can deliver up to 2X faster inference on AMD Instinct™ MI300X GPUs compared to non-AITER runs.| AMD ROCm Blogs
Training large language models (LLMs) at scale is inherently complex. Different frameworks expose inconsistent interfaces, multi-GPU and distributed setups require brittle scripting, and backend-specific quirks introduce overhead that slows down training iterations. Primus tackles these challenges with a streamlined, backend-agnostic training framework that helps developers launch, customize, and scale training jobs faster on AMD GPUs.| AMD ROCm Blogs
This blog introduces a novel and computationally efficient paradigm for Vision-Language Models (VLMs), which diverges from the conventional method of prepending visual tokens to textual input. Instead of elongating the input sequence, this approach injects visual information directly into the Large Language Model’s (LLM) parameters. It achieves this by using a vision encoder to extract image features and then employing a perceptual weight generator to transform these features into dynamic, ...| AMD ROCm Blogs
In our previous blog post, we introduced the Deep Graph Library (DGL) and highlighted how its support on the AMD ROCm platform unlocks scalable, performant graph neural networks (GNNs) on AMD GPUs. That post focused on the why — the growing relevance of graph workloads and what it means to bring that capability to AMD’s accelerated computing ecosystem.| AMD ROCm Blogs
This blog post will guide you through fine-tuning Wan2.2 - a state-of-the-art video generation model - on a single AMD Instinct MI300X GPU. By following this guide, you’ll unlock Wan2.2’s advanced video generation capabilities and customize the output — whether in a unique artistic style or a specialized domain — all while running memory efficiently even on a single GPU. Here are some examples of how you can put this guide into practice:| AMD ROCm Blogs
Building workflows for generative AI tasks can of course be done purely in code. However, as the interest in GenAI has soared together with its use in people’s daily lives, more and more people start to search for and explore tools and software for building GenAI workflows that do not require extensive programming knowledge. One such tool is ComfyUI, which provides users with a simple drag and drop UI for building GenAI workflows. This blog post will briefly cover what ComfyUI is, and how y...| AMD ROCm Blogs
This blog takes a closer look at recent advances in AI-powered video editing, highlighting how modern diffusion models enable users to accomplish various video editing tasks on AMD Instinct GPUs using Alibaba’s VACE model.| AMD ROCm Blogs
Enabling ROCm support for FastVideo inference using TeaCache on AMD Instinct GPUs, accelerating video generation with optimized backends| ROCm Blogs
We present AMD Hummingbird, offering a two-stage distillation framework for efficient, high-quality text-to-video generation using compact models.| ROCm Blogs
Fine-tune Llama 3.2 Vision models on AMD MI300X GPU using Torchtune, achieving 2.3× better accuracy with 11B vs 90B model on chart-based tasks.| ROCm Blogs
The blog explains the reasons behind RCCL bandwidth limitations and xGMI performance constraints, and provides actionable steps to maximize link efficiency on AMD MI300X| ROCm Blogs
A practical guide for accelerating video generation with HunyuanVideo and Wan 2.1 using Unified Sequence Parallelism on AMD GPUs.| ROCm Blogs
vLLM v1 on AMD ROCm boosts LLM serving with faster TTFT, higher throughput, and optimized multimodal support—ready out of the box.| ROCm Blogs
Simplify GPU acceleration in containers with the AMD Container Toolkit—streamlined setup, runtime hooks, and full ROCm integration.| ROCm Blogs
vLLM v0.9.x is here with major ROCm™ optimizations—boosting LLM performance, reducing latency, and expanding model support on AMD Instinct™ GPUs.| ROCm Blogs
Part 1 of our GPU profiling series introduces ROCm tools, setup steps, and key concepts to prepare you for deeper dives in the posts to follow.| ROCm Blogs
Learn how to leverage Model Context Protocol (MCP) servers to provide real time context information to LLMs through a chatbot example on AMD GPUs| ROCm Blogs
Follow this step-by-step guide to reproduce AMDs MLPerf 5.0 Training Submission with Instinct GPUs using ROCm| ROCm Blogs
A step-by-step guide to reproducing AMD’s MLPerf v5.0 results for Llama 2 70B & SDXL using ROCm on MI325X| ROCm Blogs
AMD is excited to announce Instella, a family of fully open state-of-the-art 3-billion-parameter language models (LMs). , In this blog we explain how the Instella models were trained, and how to access them.| ROCm Blogs
AMD's GPU training optimizations deliver peak performance for advanced AI models through ROCm software stack.| ROCm Blogs
Learn how to optimize large language model inference using vLLM on AMD's MI300X GPUs for enhanced performance and efficiency.| ROCm Blogs
This post, the second in a series, provides a walkthrough for building a vLLM container that can be used for both inference and benchmarking.| ROCm Blogs
Featured Posts| rocm.blogs.amd.com
In this post we present a brief preview of AMD's Next-Gen Fortran Compiler, our new open source Fortran complier optimized for AMD GPUs using OpenMP offloading, offering direct interface to ROCm and HIP.| ROCm Blogs
