We are pleased to announce the release of zml/llmd 20261106.0. This week, we are bringing two new models,
asynchronous scheduling in beta, and more performance work across our backends.
This release brings support for [Reflection’s Beam 1.0](https://huggingface.co/reflection/Beam-1.0-501B-A23B) and
Day 1 support for [Ricursive’s Ripple](https://huggingface.co/ricursiveAI/Ripple-65B-Preview) (well, technically Day 0, but
we didn’t want to derail the release).
Here is the full list of models supported by zml/llmd:
We have added asynchronous scheduling to Llama and Gemma 4. The idea is simple: while the accelerator is running one step, the CPU can prepare the next one. Less time waiting between steps.
source & further reading
zml.ai — original article
zml/llmd 20261029.0
zml/llmd 20261023.0
The Universal LLM Server