{"type":"post","id":"omlx-0-8-0rc1-adds-prefill-accelerator-using-780453","slug":"omlx-0-8-0rc1-adds-prefill-accelerator-using-780453","title":"oMLX 0.8.0rc1 adds Prefill Accelerator using NVIDIA GPUs or a second Mac","description":"oMLX 0.8.0rc1 adds a Prefill Accelerator that lets a faster NVIDIA-equipped PC or second Mac handle the first layers of prompt chunks while a primary Mac completes inference.","retrieval_nugget":"oMLX 0.8.0rc1 adds a Prefill Accelerator that lets a faster NVIDIA-equipped PC or second Mac handle the first layers of prompt chunks while a primary Mac completes inference. The maintainer reports large prefill gains on long prompts, offering local-model builders a way to reduce prompt-processing time without moving decode or the KV cache off the Mac.","published_at":"2026-11-12","updated_at":"2026-11-12","record_date":"2026-11-12","date_kind":"published_at","topics":["inference"],"entities":["oMLX","NVIDIA DGX Spark","NVIDIA RTX A6000","DeepSeek V4.1","Qwen3.8"],"related_patterns":["agent-economics-moves-to-completed-work"],"novelty_label":"new_fact","what_changed":"oMLX 0.8.0rc1 adds prefill acceleration using NVIDIA GPUs or a second Mac.","prior_refs":["https://newruntime.com/posts/omlx-0-7-3-speeds-up-deepseek-v4-fd0577/"],"source_url":"https://github.com/jundot/omlx/releases/tag/v0.8.0rc1","source_urls":["https://github.com/jundot/omlx/releases/tag/v0.8.0rc1"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:omlx-0-8-0rc1-adds-prefill-accelerator-using-780453","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/omlx-0-8-0rc1-adds-prefill-accelerator-using-780453/","markdown":"https://newruntime.com/posts/omlx-0-8-0rc1-adds-prefill-accelerator-using-780453.md","json":"https://newruntime.com/posts/omlx-0-8-0rc1-adds-prefill-accelerator-using-780453.json"},"markdown_url":"https://newruntime.com/posts/omlx-0-8-0rc1-adds-prefill-accelerator-using-780453.md","next_reads":[{"type":"topic","path":"/topics/inference/","url":"https://newruntime.com/topics/inference/","title":"Inference","reason":"Explore the inference topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/inference.md","json_url":"https://newruntime.com/topics/inference.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}