🚀 Automated installation script for vLLM on HPC systems with ROCm support, optimized for AMD MI300X GPUs.

Inference scaling benchmark of Qwen3.5-2B on AMD Instinct MI300X using ROCm and Hugging Face Transformers.

White paper & reproducible benchmark suite for LLM inference optimization on AMD MI300X using ROCm 6.1

Agentic CUDA-to-ROCm migration loop - translates, compiles, profiles, and iteratively fixes GPU kernels with real hardware feedback.

Zero-Knowledge multi-agent DAO governance on AMD MI300X + ROCm 6.2. AI agents propose, humans vote privately, treasury executes via ZK proofs. 🤗 HF Space: https://huggingface.co/spaces/XMRTDAO/zero-claw

Meridian — An AI-first project management platform featuring a serverless architecture powered by React and an AMD MI300X Inference Endpoint.

Domain-specific fine-tuned code model for AMD ROCm GPU kernel optimization. SFT + GRPO on MI300X. 14% vs CUDA hand-tuned. 🤗 HF Space: https://huggingface.co/spaces/XMRTDAO/rocm-kernel-tuner

Span-cited English investor memos from Japanese 有価証券報告書, produced by a 14B nekomata-qfin fine-tune on a single AMD Instinct MI300X.