Buscar en todos los blogs
Noticias y anuncios
-
Accelerating Generative AI: How AMD Instinct™ GPUs Delivered Breakthrough Efficiency and Scalability in MLPerf Inference v5.1
Discover MLPerf Inference v5.1 results showcasing FP4 efficiency, structured pruning, seamless scaling, and partner-proven performance at scale.
September 09, 2025
-
AU 2025: Autodesk Software and AMD A-Go-Go
AU 2025 starts on Sept 16 and AMD will be showcasing new systems. See how AMD Ryzen AI PRO CPUs can transform your projects – no discrete GPU required…
September 09, 2025
-
AMD Instinct MI350 Series GPUs: A Game Changer for Inference, Training and HPC Workloads
AMD Instinct™ MI350 GPUs deliver faster training, larger model support, and scalable AI performance—without lock-in or proprietary constraints.
September 08, 2025
-
Dell x AMD: Reinventing Workstations, Advancing AI
Great collaborations yield incredible results. Learn how Dell and AMD are reshaping computing.
September 05, 2025
-
AMD Announces 100k Hours of Free Developer Cloud Access to Indian Researchers and Startups
AMD will provide 100,000 hours of free Developer Cloud access over the next year to Indian researchers and startups to promote open ecosystems, and tr…
September 05, 2025
-
Competitive KX Nano Benchmarking on AMD EPYC Processors
KX is the provider of the high-performance time series analytical database, kdb+, which is widely adopted across financial services institutions for h…
September 04, 2025
-
The Right CPU can Boost Microsoft SQL Server® Performance and Lower Software Costs
Learn how choosing the right CPU can boost performance and lower software licensing costs.
September 03, 2025
Artículos técnicos y blogs
-
GEMM Tuning within hipBLASLt - Part 1 — ROCm Blogs
We introduce a hipBLASLt tuning tool that lets developers optimize GEMM problem sizes and integrate them into the library.
September 04, 2025
-
Step-3 Deployment Simplified: A Day 0 Developer’s Guide on AMD Instinct™ GPUs — ROCm Blogs
Learn how to deploy Step-3, a 321B-parameter VLM with MFA & AFD, on AMD Instinct™ GPUs to cut decoding costs and boost long-context reasoning
September 03, 2025
-
Unleashing AMD Instinct™ MI300X GPUs for LLM Serving: Disaggregating Prefill & Decode with SGLang — ROCm Blogs
Learn how prefill–decode disaggregation improves LLM inference by reducing latency, enhancing throughput, and optimizing resource usage.
August 27, 2025
-
QuickReduce: Up to 3x Faster All-reduce for vLLM and SGLang — ROCm Blogs
Quick Reduce speeds up LLM inference on AMD Instinct™ MI300X GPUs with inline-compressed all-reduce, cutting comms overhead by up to 3×
August 25, 2025
-
AITER-Enabled MLA Layer Inference on AMD Instinct MI300X GPUs — ROCm Blogs
AITER boosts DeepSeek-V3’s MLA on AMD MI300X GPUs with low-rank projections, shared KV paths & matrix absorption for 2× faster inference.
August 24, 2025
-
Primus: A Lightweight, Unified Training Framework for Large Models on AMD GPUs — ROCm Blogs
Primus streamlines LLM training on AMD GPUs with unified configs, multi-backend support, preflight validation, and structured logging.
August 21, 2025
-
Introducing AMD EVLM: Efficient Vision-Language Models with Parameter-Space Visual Conditioning — ROCm Blogs
A novel approach that replaces visual tokens with perception-conditioned weights, reducing compute while maintaining strong vision-language performanc…
August 21, 2025
-
Real-time Edge-optimized AI powered Parallel Pixel-upscaling Engine on AMD Ryzen AI
In this blog post, we describe the engineering decisions, architecture, and optimizations behind our solution—and present real-world performance bench…
August 21, 2025
