AMD ROCm Blogs
- Posts
- 29 from 14 Oct 2026 to 6 Nov 2026
- Posting
- weekly (29 in the last year)
- Kind
- company blog
- Feed
- https://rocm.blogs.amd.com/blog/atom.xml
2026 29
- ROCm InferaSim: Cut LLM Serving Trial Costs and Deploy the Best Configuration
- PrimusClaw: An Open-Source Managed Agent Runtime for AMD Instinct GPU Clusters
- Online Quantization: Smooth Path from One Checkpoint to Any Desired Serving Scenario
- From Operator to Kernel: Profile DeepSeek-V4-Flash in Primus with madengine
- Quark Mixed-Precision Quantization for Wan2.2 Video Generation on AMD Instinct GPUs
- Performance Profiling on AMD GPUs - Part 7: AI/PyTorch® Edition
- GLM-5.2 AgentX on AMD Instinct MI355X: Boosting Throughput and Interactivity
- FlyDSL Mono Kernels for High-Interactivity LLM Serving in ATOM
- How to Scale Diffusion Inference Across AMD RDNA 4 GPUs
- Faster Stable Diffusion on AMD Ryzen™ AI with TeaCache
- Device Memory Load Issue Stalls and Scheduling Opportunities in Lock-Stepped Kernels on AMD Instinct™ MI300X
- Bringing the MONAI Model Zoo to AMD Instinct™ GPUs: Validated Inference on ROCm
- DeepSeek-V4 Flash RL on AMD Instinct MI308X GPUs with an AITER-Backed RL Stack
- Two Waves, One Stage Apart: Warp-Pipelining Triton GEMMs on AMD Instinct
- Training EAGLE3 Speculative Decoding Draft Models on AMD Instinct MI350X with AMD Quark
- ROCm 10.0.0 Support for Ray 2.58.0: Enabling Scalable AI Workflows
- Accelerating MONAI Digital-Pathology Pipelines on AMD Instinct™ GPUs with hipCIM
- Ultralytics YOLO on AMD GPUs: Train, Run, and Deploy with ROCm™
- Group-GEMM in XLA: Making Mixture-of-Experts Fast and Memory-Efficient
- Scaling 3D Gaussian Splatting with Distributed Compute: Why One GPU Is Never Enough
- FP8 GEMM Optimization on AMD RDNA™ 4 Architecture
- Optimizing World Action Models on AMD GPUs
- MoE Training Optimization with Primus
- Micro-World 2: Streaming Real-time Interactive World Model
- hipCIM 26.06: GPU-Accelerated Whole-Slide Image I/O on AMD Instinct™ GPUs
- Introducing rocOpt: GPU-Accelerated Decision Optimization on AMD ROCm
- Bringing Ultra-Fast, Interactive LLM Inference to AMD Instinct™ MI355X GPUs
- 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