{"type":"post","id":"disaggregated-quantization-disaggregated-quantization-official-codebase-3c1bec","slug":"disaggregated-quantization-disaggregated-quantization-official-codebase-3c1bec","title":"disaggregated-quantization: Disaggregated quantization official codebase","description":"IST-DASLab has released code and checkpoints for disaggregated quantization, a method that assigns different quantization choices to prompt processing and token generation.","retrieval_nugget":"IST-DASLab has released code and checkpoints for disaggregated quantization, a method that assigns different quantization choices to prompt processing and token generation. Its reported gains suggest that teams exploring very low-bit inference may recover useful accuracy or reduce prompt latency, but the results are tied to specific models and evaluation setups.","published_at":"2026-11-13","updated_at":"2026-11-13","record_date":"2026-11-13","date_kind":"published_at","topics":["inference","models","open-source"],"entities":["IST-DASLab","Disaggregated Quantization","Qwen3","Gemma 3","NVFP4"],"related_patterns":["agent-economics-moves-to-completed-work"],"novelty_label":"new_fact","what_changed":"A GPU MODE talk on disaggregated quantization is scheduled for today at 19:00 UTC.","prior_refs":[],"source_url":"https://github.com/IST-DASLab/disaggregated-quantization","source_urls":["https://github.com/IST-DASLab/disaggregated-quantization"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:disaggregated-quantization-disaggregated-quantization-official-codebase-3c1bec","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/disaggregated-quantization-disaggregated-quantization-official-codebase-3c1bec/","markdown":"https://newruntime.com/posts/disaggregated-quantization-disaggregated-quantization-official-codebase-3c1bec.md","json":"https://newruntime.com/posts/disaggregated-quantization-disaggregated-quantization-official-codebase-3c1bec.json"},"markdown_url":"https://newruntime.com/posts/disaggregated-quantization-disaggregated-quantization-official-codebase-3c1bec.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":"topic","path":"/topics/models/","url":"https://newruntime.com/topics/models/","title":"Models","reason":"Explore the models topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/models.md","json_url":"https://newruntime.com/topics/models.json"},{"type":"topic","path":"/topics/open-source/","url":"https://newruntime.com/topics/open-source/","title":"Open Source","reason":"Explore the open-source topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/open-source.md","json_url":"https://newruntime.com/topics/open-source.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"}]}