{"type":"post","id":"humans-released-gpu-accelerated-weight-teleportation-lossless-rl-d8d2b5","slug":"humans-released-gpu-accelerated-weight-teleportation-lossless-rl-d8d2b5","title":"humans& released GPU-accelerated Weight Teleportation, lossless RL weight sync faster than intra-cluster RDMA.","description":"humans& describes a lossless GPU-accelerated pipeline for synchronizing reinforcement-learning weights between trainers and rollout samplers.","retrieval_nugget":"humans& describes a lossless GPU-accelerated pipeline for synchronizing reinforcement-learning weights between trainers and rollout samplers. On its Ampersand production configuration, the company reports end-to-end sync below four seconds and sampler pauses below 0.23 seconds, a result that matters when weight handoffs constrain RL iteration speed.","published_at":"2026-11-03","updated_at":"2026-11-07","record_date":"2026-11-03","date_kind":"published_at","topics":["ai-infrastructure","compute"],"entities":["humans&","Weight Teleportation","Ampersand","SGLang","Miles","GLM-5.3","NVIDIA Blackwell"],"related_patterns":[],"novelty_label":"new_fact","what_changed":"humans& introduces GPU-accelerated, lossless Weight Teleportation for RL weight sync, claiming speeds that can exceed intra-cluster RDMA; the prior covers Baseten’s delta weight sync work.","prior_refs":["https://newruntime.com/posts/the-fastest-delta-weight-syncs-in-the-world-9f8e72/"],"source_url":"https://humansand.ai/blog/gpu-accelerated-weight-teleportation","source_urls":["https://humansand.ai/blog/gpu-accelerated-weight-teleportation"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:humans-released-gpu-accelerated-weight-teleportation-lossless-rl-d8d2b5","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/humans-released-gpu-accelerated-weight-teleportation-lossless-rl-d8d2b5/","markdown":"https://newruntime.com/posts/humans-released-gpu-accelerated-weight-teleportation-lossless-rl-d8d2b5.md","json":"https://newruntime.com/posts/humans-released-gpu-accelerated-weight-teleportation-lossless-rl-d8d2b5.json"},"markdown_url":"https://newruntime.com/posts/humans-released-gpu-accelerated-weight-teleportation-lossless-rl-d8d2b5.md","next_reads":[{"type":"topic","path":"/topics/ai-infrastructure/","url":"https://newruntime.com/topics/ai-infrastructure/","title":"Ai Infrastructure","reason":"Explore the ai-infrastructure topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/ai-infrastructure.md","json_url":"https://newruntime.com/topics/ai-infrastructure.json"},{"type":"topic","path":"/topics/compute/","url":"https://newruntime.com/topics/compute/","title":"Compute","reason":"Explore the compute topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/compute.md","json_url":"https://newruntime.com/topics/compute.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"}]}