ZML/LLMD alpha
Today we’re releasing ZML/LLMD. It’s a self-contained inference server that runs LLaMa, Gemma, Qwen and Mistral LLMs transparently on 5 architectures: NVIDIA CUDA, AMD ROCm, Google TPU, Intel oneAPI and Apple Metal.
10x faster tokenization
Apr 7, 2026
Today we merged a pretty nice performance improvement to ZML.
Introducing zml-smi
Mar 30, 2026
zml-smi is a universal diagnostic and monitoring tool for GPUs, TPUs and NPUs. It provides real-time insights into the performance and health of your hardware.
Introducing ZML/v2
Mar 24, 2026
ZML is an inference stack built close to the hardware. It lowers models directly onto NVIDIA, AMD, TPU, and Trainium targets from a single codebase, without depending on and suffering from the Python-heavy runtime layers that most of the ecosystem is built around.