Anyscale 推出 LLM 生产化培训课程，涵盖 SkyRL 强化学习实战
Anyscale 开了门课，教你用 SkyRL 做后训练，从 GRPO 到终端智能体案例都带上手 demo，想搞 RL 工程的可以看看。
Anyscale 推出一门面向生产环境的 LLM 后训练与推理优化课程。课程内容包括 RLVR 与 GRPO 的入门、On-policy Distillation 与多教师版本 MOPD 等后训练方法。实战案例是后训练一个终端智能体，涉及构建 eval、自定义环境和 RL 系统。演示部分使用 SkyRL 展示全异步 RL 流程，以及 RL rollout 的性能监控和调优。
Learn how to productionize large language models using distributed post-training and inference optimization techniques. Participants will explore advanced LLM post-training techniques, including agentic reinforcement learning with SkyRL.
Hands-on topics include: - Intro to LLM post-training - Intro to RLVR (with GRPO) - Recent development of LLM post-training: - On-policy distillation (OPD) and Multi-teacher On-policy distillation (MOPD) - Case study: Post-training a terminal agent - Building evals - Building custom environments - RL systems - Demo walkthrough - Intro to SkyRL - Full Async RL with SkyRL - Performance monitoring and tuning for RL rollouts
Register: https://t.co/jSyIouwg97
- PyTorch10-21 20:01原文
