Recent Posts - Page 2#
Continuing the Momentum: Refining ROCm For The Next Wave Of AI and HPC
ROCm 7.1 builds on 7.0’s AI and HPC advances with faster performance, stronger reliability, and streamlined tools for developers and system builders.
Retrieval Augmented Generation (RAG) with vLLM, LangChain and Chroma
Learn AI-powered knowledge retrieval that enriches prompts with proprietary data to deliver accurate and context-aware answers
Stability at Scale: AMD’s Full‑Stack Platform for Large‑Model Training
Primus streamlines LLM training on AMD GPUs with unified configs, multi-backend support, preflight validation, and structured logging.
High-Accuracy MXFP4, MXFP6, and Mixed-Precision Models on AMD GPUs
Learn to leverage AMD Quark for efficient MXFP4/MXFP6 quantization on AMD Instinct accelerators with high accuracy retention.
Nitro-E: A 304M Diffusion Transformer Model for High Quality Image Generation
Nitro-E is an extremely lightweight diffusion transformer model for high-quality image generation with only 304M paramters.
STX-B0T: Real-time AI Robot Assistant Powered by RyzenAI and ROCm
STX-B0T explores the potential of RyzenAI PCs to power robotics applications on NPU+GPU. This blog demonstrates how our hardware and software interoperate to unlock real-time perception.
Performance Profiling on AMD GPUs - Part 3: Advanced Usage
Part 3 of our GPU profiling series guides beginners through practical steps to identify and optimize kernel bottlenecks using ROCm tools
Empowering Developers to Build a Robust PyTorch Ecosystem on AMD ROCm™ with Better Insights and Monitoring
Production ROCm support for N-1 to N+1 PyTorch releases is in progress. The AI Software Head-Up Dashboard shows status of PyTorch on ROCm.
ROCm 7.9 Technology Preview: ROCm Core SDK and TheRock Build System
Introduce ROCm Core SDK, and learn to install and build ROCm components easily using TheRock.
Kimi-K2-Instruct: Enhanced Out-of-the-Box Performance on AMD Instinct MI355 Series GPUs
Learn how AMD Instinct MI355 Series GPUs deliver competitive Kimi-K2 inference with faster TTFT, lower latency, and strong throughput.
Gumiho: A New Paradigm for Speculative Decoding — Earlier Tokens in a Draft Sequence Matter More
Gumiho boosts LLM inference with early-token accuracy, blending serial + parallel decoding for speed, accuracy, and ROCm-optimized deployment.
GEMM Tuning within hipBLASLt– Part 2
Learn how to use hipblaslt-bench for offline GEMM tuning in hipBLASLt—benchmark, save, and apply custom-tuned kernels at runtime.