Orbit - Ultra-efficient RL Pipeline

Orbit — Ultra-efficient RL Pipeline

Orbit is an open-source RL framework for memory-efficient post-training of trillion-parameter LLMs. By minimizing the train-rollout gap in RL, Orbit is able to effortlessly train Kimi-K2.6 and DeepSeek V4-pro at a single-node setting . Five rollout architectures, one shared clock, clear win for Orbit's design Watch the bottleneck move. We start fully serial with a full-weight push (basesline 1 below), then test the tokens "is the heavy push the bottleneck?" . We gradually turn the baseline into Orbit's final design (+ overlap (async); + adapter-native push; + a non-blocking double-buffered swa

saved by

• Alex K

related reading

• You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectoriesarxiv.org
• Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusionarxiv.org
• LoRA Without Regret - Thinking Machines Labthinkingmachines.ai
• frontier model training methodologies | Alex Wa's Blogdjdumpling.github.io
• Keep the Tokens Flowing: Lessons from 16 Open-Source RL Librarieshuggingface.co
• RL at 1T Scale: prime-rl Performance Deep Diveprimeintellect.ai
• The Extreme Inefficiency of RL for Frontier Models - Toby Ordtobyord.com
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• How can LLM RL Work Despite Information-Theoretic Inefficiencyberen.io
• >10x More Efficient Pretraining — Magicmagic.dev
• Is Frontier Asynchronous RL Solved? — Luke J. Huangluk-huang.github.io
• [2604.13010] Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillationarxiv.org