Recent Posts - Page 7#
Fine-Tune LLMs for Proteins with AMD Enterprise AI Suite
Fine-tune Llama 3.1 8B with ROCm for advanced protein sequence insights in bioinformatics
Using Reinforcement Learning to Fix Text in AI-Generated Videos
Demonstrates how Flow-GRPO can be used to fine-tune Wan models to better generate text in videos by covering background, set up and some examples of training runs.
The vLLM MoE Playbook: A Practical Guide to TP, DP, PP and Expert Parallelism
Learn how to combine TP, DP, PP, and EP for MoE models. Discover proven strategies to maximize performance on your vLLM deployments.
LuminaSFT: Generating Synthetic Fine-Tuning Data for Small Language Models
Learn how task-specific synthetic data can improve small language model performance and explore results from the LuminaSFT study.
Inference with HunyuanWorld-Voyager on AMD Instinct GPUs
Learn how to run inference with HunyuanWorld-Voyager, a state-of-the-art 3D world model, on AMD Instinct MI300X GPUs using ROCm for efficient video generation and prediction.
Accelerating AI-Driven Crystalline Materials Design with MatterGen on AMD Instinct MI300X
Learn how to run a generative model for inorganic material design with MatterGen on MI300X.
AMD Inference Microservice (AIM): Production Ready Inference on AMD Instinct™ GPUs
Learn how AIM delivers efficient, scalable inference on AMD Instinct GPUs and see how it simplifies deployment, optimization, and operations.
AMD Enterprise AI Suite: Open Infrastructure for Production AI
Explore an open, GPU-optimized platform to build, deploy, and scale enterprise AI workloads on AMD Instinct with production-ready performance.
Plug-and-Play CuPy on ROCm: Data Analytics Acceleration Made Simple
Learn about how to enhance your analytics project with the latest AMD CuPy release.
Democratizing AI Compute with AMD Using SkyPilot
Learn how SkyPilot integrates with AMD open AI stack to enable seamless multi-cloud deployment and simplifies NVIDIA-to-AMD GPU migration.
Accelerating Vector Search: hipVS and hipRAFT on AMD
Learn how hipVS accelerates vector search on AMD Instinct GPUs, with notebook demos for semantic search, RAG, and recommendation systems.
Practical, Fault‑Robust Distributed Inference for DeepSeek on AMD MI300X
Learn how a small-radius expert parallel design with prefill–decode disaggregation enables scalable, fault-isolated LLM inference on AMD Instinct™ MI300X clusters.