zml/llmd 20261106.0

Zml/llmd released version 20261106.0, adding support for Reflection's Beam 1.0 (501B-A23B) and Day 1 support for Ricursive's Ripple (65B-Preview), plus beta asynchronous scheduling for Llama and Gemma 4. The asynchronous scheduling lets the CPU prepare the next step while the accelerator runs the current one, reducing wait time between steps, and the release also includes performance work across backends.

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.