搜尋所有部落格
新聞與公告
-
AMD Accelerates Kodiak AI’s New Autonomous Driving Platform with EPYC Processors
AMD EPYC processors are powering Kodiak AI’s seventh generation autonomous truck platform, delivering improved compute performance, processing speed a…
August 26, 2026
-
MetaRoCE: Evolving Network Transports for AI
Learn how MetaRoCE helps optimize AI training networks with multipath transport and how AMD programmable AI NICs support rapid protocol evolution.
August 25, 2026
-
Cloud AI Costs Are Growing: How Hybrid AI Can Help
See how hybrid AI can help manage cloud AI costs by balancing local and cloud workloads with the AMD Tokenomics Calculator.
August 25, 2026
-
-
-
Modern Security from Silicon to OS: Why SMBs Should Move Beyond Windows Server 2016
Windows Server 2016 support is ending. Modernize SMB and ROBO security with Windows Server 2025 and AMD EPYC 4005 CPUs.
August 17, 2026
-
Think Video Connectivity, Think NDI — Advanced by AMD
The future of video connectivity is not only about moving pixels from one place to another. It is about enabling flexible, intelligent and scalable wo…
August 17, 2026
-
Run Qwen 3.8 27B on AMD Ryzen™ AI Max Agentic PCs and Radeon ™ GPUs
Qwen3.8 27B arrives with Day 0 support on AMD Ryzen™ AI processors and Radeon™ graphics cards. Run the latest Qwen model locally with LM Studio on sup…
August 14, 2026
技術文章與部落格
-
Lessons from the AMD DevMaster Hackathon
Explore lessons from the AMD DevMaster Hackathon, where developers built practical Multimodal, Agentic, and Physical AI applications on AMD Radeon™ GP…
August 26, 2026
-
Enabling Physical AI Agents with Lemonade — ROCm Blogs
Learn to deploy local agents for interactive robot arm manipulation using the Lemonade framework.
August 24, 2026
-
How an AI Agent Improves the AMD Quark User Experience
Quark AI Agent Skills provides a guided, conversational approach to model quantization, enabling users to easily prepare PyTorch and ONNX models for A…
August 24, 2026
-
Serving 64Mi-Token Contexts on One AMD Instinct™ MI355X Node — ROCm Blogs
Explore how one 8-GPU AMD MI355X node serves Kimi Linear from 1K to 64M tokens under vLLM—and the TTFT and decode throughput behind the run.
August 23, 2026
-
DI Series: Scaling GLM-5.1-FP8 to 64 MI300X GPUs — ROCm Blogs
Scale GLM-5.1-FP8 long-context serving beyond a single node on AMD Instinct MI300X with WideEP prefill-decode disaggregation and MoRI.
August 20, 2026
-
llama cpp on AMD EPYC
Discover how ZenDNN accelerates llama.cpp on AMD PYC™ processors with optimized CPU kernels and benchmarks.
August 18, 2026
-
Scaling RL with verl on AMD Instinct MI355X: Async Walkthrough and Sync Benchmark — ROCm Blogs
Scale RLHF on AMD Instinct MI355X with verl's fully async trainer. Hands-on GRPO + DAPO examples.
August 17, 2026
-
Exploring XGBoost: A Deep Dive — ROCm Blogs
A single source explanation of XGBoost features and its working principles.
August 17, 2026
