DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts
cs.LG
Submitted: 2026-05-14
Updated: 2026-11-02
Code: https://github.com/amazon-science/dualkv-flash-attn-for-rl
Terminology
Sources
- Bifurcated Attention: Accelerating Massively Parallel Decoding with Shared Prefixes in LLMs
- Training Verifiers to Solve Math Word Problems
- The Llama 3 Herd of Models
- OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
- REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
- DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models
- LongReason: A Synthetic Long-Context Reasoning Benchmark via Context Expansion
- Prefix Grouper: Efficient GRPO Training through Shared-Prefix Forward
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Qwen3 Technical Report
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis