搜尋所有部落格
新聞與公告
-
AMD Ryzen™ AI PCs: A Portfolio Built for the Future
Whether you’re a gamer or content creator, or need a high powered system for productivity or entertainment, there is an AI PC for everyone.
June 12, 2026
-
AMD, Dell Technologies and the University of Cambridge Launch UK Sovereign AI Innovation Lab
AMD, Dell Technologies and the University of Cambridge announce plans to establish the new Sovereign AI Innovation Lab in the United Kingdom.
June 10, 2026
-
Agentic AI Needs Rack-Scale Execution AMD EPYC™ Delivers It
AMD EPYC delivers higher deployable CPU throughput, x86 software continuity and a standards-based path to dense, AI-supporting infrastructure.
June 09, 2026
-
AMD Silo AI & Delphyr AI Collaborate to Scale Practical Clinical AI
AMD Silo AI and Delphyr AI deliver scalable, privacy-first clinical AI: faster EHR retrieval, high-performance embeddings, and seamless workflow integ…
June 02, 2026
-
Advancing Windows ML Acceleration with AMD at Microsoft Build 2026
It's time for Microsoft Build 2026, and we've got a bevy of AI compatibility and performance improvements to discuss. Further details discussed within…
June 02, 2026
-
1.5.0 SDK Announcement
AMD Alveo MA35D AMA SDK 1.5.0: Keeping MA35D Current and Ready for Next Gen Video Workflows
June 01, 2026
-
AMD and Hack Club Launch Stardance
AMD teams with Hack Club, NASA, and GitHub Education for Stardance Challenge, a nationwide summer engineering competition for students to build real-w…
June 01, 2026
-
AMD FPGAs Power ModRetro M64 Retro Gaming Revival
See how AMD Artix UltraScale+ FPGAs help ModRetro's M64 deliver authentic, low-latency retro gaming with original N64 cartridges.
June 01, 2026
技術文章與部落格
-
Day 0 Support for MiniMax M3 on AMD Instinct GPUs
MiniMax M3 is a new open-weight model for coding, agentic, and multimodal workloads. MiniMax describes M3 as combining three frontier capabilities in …
June 12, 2026
-
AMD at Microsoft Build 2026
AMD joined developers, engineers, and AI builders at Microsoft Build 2026 in San Francisco, hosting four hands-on workshops that brought the AMD AI ec…
June 12, 2026
-
Upscale Everything Super-Resolution Across AMD Hardware
This blog covers four ways developers can implement or use super-resolution on AMD hardware, whether they are building games, local AI apps, NPU workf…
June 11, 2026
-
AMD PACE integrates with vLLM
Run transformer models more efficiently on AMD EPYC™ CPUs with the AMD PACE vLLM plugin and its optimized inference backends.
June 11, 2026
-
Low Kruskal-Rank Adaptation — ROCm Blogs
Learn how Kruskal rank can enhance LoRA by replacing the conventional matrix-rank formulation for more efficient training.
June 10, 2026
-
Productionizing TurboQuant on AMD GPUs for KV-Cache-Bound LLM Inference — ROCm Blogs
Productionized TurboQuant 4-bit KV-cache quantization on AMD GPUs via vLLM, with custom kernels and accuracy analysis on agentic workloads.
June 10, 2026
-
AMD Instinct MI355X GPU Sets a New Bar for DeepSeek Inference
In this blog, we highlight how AMD Instinct™ MI355X sets a new bar for DeepSeek V4 inference, combining industry-leading performance, cost-efficient t…
June 10, 2026
-
Accelerating Local LLM Conversations with KV Cache Reuse on AMD Ryzen AI
KV cache reuse helps reduce latency in multi-turn LLM applications by preserving the model's internal attention state and processing only newly added …
June 10, 2026
