すべてのブログを検索
ニュースと発表
-
Adaptive: Build on Innovation; Design for What's Next
AMD delivers a portfolio of CPU, GPU, FPGA, adaptive SoC, NPU and networking IP to help customers match each workload to the right architecture.
October 27, 2026
-
AMD Pensando™ DPUs: A Programmable Foundation for AMD-Based Oracle Acceleron SmartNICs
AI is entering a new phase. Training, inference, and agentic AI systems are becoming more capable, distributed, and central to how organizations opera…
October 27, 2026
-
NeuroSpark Expands AI Compute Choice with AMD
NeuroSpark uses AMD Instinct GPUs and ROCm software on OCI to deliver flexible, cost-effective AI training and inference
October 23, 2026
-
Sovereign AI for European Customer Conversations
LeadDesk, QuTwo, and AMD Silo AI collaborate on a sovereign AI stack that brings near-frontier, open-weight models to European customer conversations.
October 22, 2026
-
AMD and Advantech - Architecting the Next Generation of Regulated Casino Games
Discover how Advantech and AMD are redefining regulated casino gaming with Ryzen Embedded 8000 Series processors, integrated RDNA 3 graphics, XDNA AI …
October 21, 2026
-
From Prompt to Playback: Nunchux Turns AMD Instinct™ GPU Performance into Responsive Video AI
See how AMD Instinct™ MI355X GPUs and AMD ROCm™ software enable faster-than-playback MiniMax-H3 video generation.
October 19, 2026
-
From AI That Answers to AI That Acts
Why physical AI requires a new definition of performance – one built around the whole system, not peak compute.
October 19, 2026
-
Absci Accelerates AI Antibody Design on AMD Instinct™ GPUs
AMD and Absci achieved a 3x speedup in AI antibody design by running the AbsciBind co-folding model on Instinct™ GPUs with optimized Triton kernels.
October 18, 2026
技術記事とブログ
-
ROCm 10.0.0 Support for Ray 2.58.0: Enabling Scalable AI Workflows — ROCm Blogs
ROCm 10.0.0 with Ray 2.58.0 continues PyTorch 2.12 and vLLM support.
October 26, 2026
-
Two Waves, One Stage Apart: Warp-Pipelining Triton GEMMs on AMD Instinct — ROCm Blogs
Use warp-pipelining to overlap matrix work and data preparation in compute-bound Triton GEMMs on AMD Instinct GPUs.
October 26, 2026
-
Training EAGLE3 Speculative Decoding Draft Models on AMD Instinct MI350X with AMD Quark — ROCm Blogs
Learn how the AMD Quark team trains EAGLE3.1 draft models from scratch on AMD Instinct MI350X GPUs using ROCm, vLLM, TorchSpec, and SPEED-Bench.
October 26, 2026
-
Accelerating MONAI Digital-Pathology Pipelines on AMD Instinct™ GPUs with hipCIM — ROCm Blogs
In this blog you will measure a MONAI digital-pathology pipeline on AMD Instinct™ GPUs using hipCIM as the WSIReader backend.
October 25, 2026
-
Group-GEMM in XLA: Making Mixture-of-Experts Fast and Memory-Efficient — ROCm Blogs
Learn how to make JAX/MaxText MoE training more efficient with two new OpenXLA Group-GEMM backends for ragged-dot: ROCm hipBLASLt and generic Triton.
October 25, 2026
-
Ultralytics YOLO on AMD GPUs: Train, Run, and Deploy with ROCm™ — ROCm Blogs
Learn how to train, run, and deploy Ultralytics YOLO26 models on AMD GPUs with PyTorch on ROCm and MIGraphX, starting with Ultralytics 8.4.171.
October 25, 2026
-
Scaling 3D Gaussian Splatting with Distributed Compute: Why One GPU Is Never Enough — ROCm Blogs
Learn how to scale 3D Gaussian splatting across GPUs with distributed training, RCCL, and real-world optimization tips for AMD Instinct GPUs
October 22, 2026
-
FP8 GEMM Optimization on AMD RDNA™ 4 Architecture — ROCm Blogs
Learn how to port an FP16 GEMM kernel to FP8 on AMD RDNA 4 and use the smaller element size to unlock larger tiles and deeper K slices.
October 22, 2026
