{"type":"post","id":"project-maya-added-a-dedicated-engine-for-minimax-088226","slug":"project-maya-added-a-dedicated-engine-for-minimax-088226","title":"Project Maya added a dedicated engine for MiniMax-M3.1-Flash","description":"Project Maya added a dedicated engine for MiniMax-M3.1-Flash, bringing the model into its local inference setup alongside GLM and DeepSeek.","retrieval_nugget":"Project Maya added a dedicated engine for MiniMax-M3.1-Flash, bringing the model into its local inference setup alongside GLM and DeepSeek. The implementation combines tensor parallelism, speculative drafting, image input and long-context KV streaming; its reported figures show what a highly configured Linux workstation can achieve, not a general performance guarantee.","published_at":"2026-11-02","updated_at":"2026-11-02","record_date":"2026-11-02","date_kind":"published_at","topics":["inference"],"entities":["Project Maya","MiniMax-M3.1-Flash","MiniMax","DeepSeek","GLM","Mia-AiLab/MiniMax-M3.1-Flash-EXL3-EAQ-v1-3.5-bpw"],"related_patterns":["harness-architecture-outlives-model-choice"],"novelty_label":"new_fact","what_changed":"The Maya engine announcement adds implementation and benchmark details: tensor parallelism, DSpark, image support, INT8 KV streaming, and measured throughput through 128K context.","prior_refs":[],"source_url":"https://github.com/mw00/project-maya/pull/477","source_urls":["https://github.com/mw00/project-maya/pull/477"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:project-maya-added-a-dedicated-engine-for-minimax-088226","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/project-maya-added-a-dedicated-engine-for-minimax-088226/","markdown":"https://newruntime.com/posts/project-maya-added-a-dedicated-engine-for-minimax-088226.md","json":"https://newruntime.com/posts/project-maya-added-a-dedicated-engine-for-minimax-088226.json"},"markdown_url":"https://newruntime.com/posts/project-maya-added-a-dedicated-engine-for-minimax-088226.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"}]}