AMD ROCm
Printed in News · rocm.blogs.amd.com
Publishes about 6 a week · last piece Oct 16, 2026
How often
about 6 a week, by the archive: 21 pieces since Sep 21, 2026.
12 weeks agothis week
Latest pieces
- FP16 GEMM Optimization on AMD RDNA™ 3 and RDNA™ 4 Architectures
- Long Context, One Node: Serving GLM-5.3-FP8 on MI300X with DP8+EP8
- AMD Instinct MI455X vs MI355X: A Technical Look at the Advancing AI 2026 Inference Numbers
- DI Series: Serving Kimi-K3 MXFP4 Wide-EP Disaggregated on AMD Instinct MI300X and MI325X
- Pre-Training Hybrid LLMs from Scratch in Primus on AMD Instinct™ GPUs
- Completing the GPU Performance Picture: Understanding TAF Alongside Peak FLOPs and MAF
- ROCm 10.1: Breaking the Data-Movement Bottleneck
- Running MolmoAct2 Robot Policy on an AMD Ryzen AI Max+ 395 Mini PC
- AIM: Unified User Experience from Profile Discovery to Deployment
- Automating Performance Bottleneck Identification with the TraceLens Agent
- Unlocking Sim2Real for a Robotic Arm with RL Accelerated by AMD Instinct GPUs
- Verl 0.9.0 on ROCm™ 10.0: Next-Generation RL Post-Training on AMD Instinct™ GPUs
- Local Quantization and Multi-Backend Deployment with AMD Quark on Strix Halo
- Model Weight Profiles: Where Do the Parameters Go?
- UltraQuant on AMD Instinct: More Efficient Agentic Serving for Qwen3.8-MXFP4
In these topics
Pick one in My Edition to read it with its neighbors.