{"slug": "zml-llmd-20261106-0", "title": "zml/llmd 20261106.0", "summary": "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.", "body_md": "We are pleased to announce the release of `zml/llmd 20261106.0`. This week, we are bringing two new models,\nasynchronous scheduling in beta, and more performance work across our backends.\n\nThis release brings support for [Reflection’s Beam 1.0](https://huggingface.co/reflection/Beam-1.0-501B-A23B) and\nDay 1 support for [Ricursive’s Ripple](https://huggingface.co/ricursiveAI/Ripple-65B-Preview) (well, technically Day 0, but\nwe didn’t want to derail the release).\n\nHere is the full list of models supported by zml/llmd:\n\nWe 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.", "url": "https://wpnews.pro/news/zml-llmd-20261106-0", "canonical_source": "https://zml.ai/posts/llmd-20261106.0/", "published_at": "2026-11-06 08:00:00+00:00", "updated_at": "2026-11-06 13:50:51.211321+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-infrastructure", "ai-tools"], "entities": ["zml/llmd", "Reflection", "Beam 1.0", "Ricursive", "Ripple", "Llama", "Gemma 4"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/zml-llmd-20261106-0", "markdown": "https://wpnews.pro/news/zml-llmd-20261106-0.md", "text": "https://wpnews.pro/news/zml-llmd-20261106-0.txt", "jsonld": "https://wpnews.pro/news/zml-llmd-20261106-0.jsonld"}}