Recent Posts#
Bringing the MONAI Model Zoo to AMD Instinct™ GPUs: Validated Inference on ROCm
Learn how to run validated inference for five MONAI Model Zoo bundles on AMD Instinct™ GPUs using a ROCm overlay.
DeepSeek-V4 Flash RL on AMD Instinct MI308X GPUs with an AITER-Backed RL Stack
Run end-to-end DeepSeek-V4 Flash reinforcement learning with an AITER-backed AMD RL stack on AMD Instinct MI308X GPUs.
Two Waves, One Stage Apart: Warp-Pipelining Triton GEMMs on AMD Instinct
Use warp-pipelining to overlap matrix work and data preparation in compute-bound Triton GEMMs on AMD Instinct GPUs.
ROCm 10.0.0 Support for Ray 2.58.0: Enabling Scalable AI Workflows
ROCm 10.0.0 with Ray 2.58.0 continues PyTorch 2.12 and vLLM support.
Training EAGLE3 Speculative Decoding Draft Models on AMD Instinct MI350X with AMD Quark
Learn how the AMD Quark team trains EAGLE3.1 draft models from scratch on AMD Instinct MI350X GPUs using ROCm, vLLM, TorchSpec, and SPEED-Bench.
Group-GEMM in XLA: Making Mixture-of-Experts Fast and Memory-Efficient
Learn how to make JAX/MaxText MoE training more efficient with two new OpenXLA Group-GEMM backends for ragged-dot: ROCm hipBLASLt and generic Triton.
Accelerating MONAI Digital-Pathology Pipelines on AMD Instinct™ GPUs with hipCIM
In this blog you will measure a MONAI digital-pathology pipeline on AMD Instinct™ GPUs using hipCIM as the WSIReader backend.
Ultralytics YOLO on AMD GPUs: Train, Run, and Deploy with ROCm™
Learn how to train, run, and deploy Ultralytics YOLO26 models on AMD GPUs with PyTorch on ROCm and MIGraphX, starting with Ultralytics 8.4.171.
FP8 GEMM Optimization on AMD RDNA™ 4 Architecture
Learn how to port an FP16 GEMM kernel to FP8 on AMD RDNA 4 and use the smaller element size to unlock larger tiles and deeper K slices.
Scaling 3D Gaussian Splatting with Distributed Compute: Why One GPU Is Never Enough
Learn how to scale 3D Gaussian splatting across GPUs with distributed training, RCCL, and real-world optimization tips for AMD Instinct GPUs
MoE Training Optimization with Primus
Learn how to speed up MoE training on AMD Instinct GPUs with Primus: a fused MoE megakernel, FP8/MXFP8 expert GEMMs, and training-at-scale tuning.
Micro-World 2: Streaming Real-time Interactive World Model
This blog demonstrates how Micro-World 2 combines precisely annotated action data, four-step diffusion distillation, and ROCm-optimized inference to deliver controllable, long-horizon, real-time world generation on a single AMD Instinct GPU through a fully open-source pipeline.