2+ hour, 7+ min ago  (482+ words) The universal LLM server. Today we're releasing ZML/LLMD. It's a self-contained inference server that runs LLa Ma, Gemma, Qwen and Mistral LLMs transparently on 5 architectures: NVIDIA CUDA, AMD ROCm, Google TPU, Intel one API and Apple Metal. ZML/LLMD supports…...