Inferact and AMD collaborate on agentic inference in vLLM for Instinct GPUs

Inferact announced an engineering collaboration with AMD to strengthen production agentic inference on AMD Instinct GPUs in vLLM. Inferact says AMD contributes the Instinct platform, ROCm engineering and AITER kernel library, while Inferact and the vLLM community contribute model integration and serving features. It says the work is already running in production on AMD Instinct clusters for Inferact Platform customers, and everything the collaboration produces will be open source.