Hello everyone! Thank you for your attention to ROLL.
ROLL has recently updated with many new features, with ROLL Flash as the core. ROLL Flash achieves significant improvements in training efficiency through its innovative asynchronous training architecture.
Below is a summary of the code updates. We will continue to iterate and improve ROLL. Welcome to join the ROLL community.
🚀 Core Highlights
- Asynchronous Training Architecture: Brand-new asynchronous generation scheduler enabling efficient pipeline overlap between generation, reward calculation, and model training
- Significant Performance Improvements: Up to 2.24× speedup in RLVR tasks and up to 2.72× speedup in Agentic tasks
- Near-linear Scaling: Maintains near-linear throughput scaling at hundred-card scale, with 8× GPU resources achieving 7.6× efficiency improvement
- Multi Off-policy Algorithm Support: Integrates multiple off-policy algorithms (Decoupled PPO, TOPR, CISPO, etc.) with performance comparable to synchronous training
🔧 Major New Features
Whether you are working on mathematical reasoning, code generation, or building real-world interactive LLM agents, ROLL Flash can help you train stronger models faster, more stably, and more cost-effectively.
The ROLL team will continue to deeply cultivate system and algorithm co-innovation for RL in LLM, dedicated to building an easy-to-use, efficient, and scalable open-source ecosystem.
Welcome to Star, try, and contribute code to advance LLM reinforcement learning toward practicality and large-scale deployment! 🌟
Hello everyone! Thank you for your attention to ROLL.
ROLL has recently updated with many new features, with ROLL Flash as the core. ROLL Flash achieves significant improvements in training efficiency through its innovative asynchronous training architecture.
Below is a summary of the code updates. We will continue to iterate and improve ROLL. Welcome to join the ROLL community.
🚀 Core Highlights
🔧 Major New Features
ROLLFlash
docs_roll/docs/English/UserGuide/async_training.mdroll/distributed/scheduler/async_generate_scheduler.pydocs_roll/docs/English/UserGuide/async_parallel_rollout.mdroll/pipeline/agentic/agentic_config.py:37docs_roll/docs/English/UserGuide/algorithms/offpolicy_setting.mdAgentic
docs_roll/docs/English/UserGuide/agentic/agentic_engineer_practice.mdroll/datasets/global_dataset.pydocs_roll/docs/English/UserGuide/agentic/agentic_engineer_practice.mddocs_roll/docs/English/UserGuide/agentic/agentic_engineer_practice.mddocs_roll/docs/English/UserGuide/agentic/agentic_engineer_practice.mddocs_roll/docs/English/UserGuide/agentic/agentic_engineer_practice.mdPerformance Optimization & Backend
roll/utils/dynamic_batching.pyDocumentation
docs_roll/docs/English/UserGuide/backend/fp8_rollout.mdWhether you are working on mathematical reasoning, code generation, or building real-world interactive LLM agents, ROLL Flash can help you train stronger models faster, more stably, and more cost-effectively.
The ROLL team will continue to deeply cultivate system and algorithm co-innovation for RL in LLM, dedicated to building an easy-to-use, efficient, and scalable open-source ecosystem.
Welcome to Star, try, and contribute code to advance LLM reinforcement learning toward practicality and large-scale deployment! 🌟