1 مستودع
Awesome GitHub RepositoriesParameter Freezing Optimizations
Memory reduction techniques that freeze backbone parameters and only update specific output heads.
Distinct from Runtime Memory Overhead Tracking: Focuses on reducing memory by freezing parameters during training rather than tracking general runtime overhead
Explore 1 awesome GitHub repository matching operating systems & systems programming · Parameter Freezing Optimizations. Refine with filters or upvote what's useful.
Awesome Parameter Freezing Optimizations GitHub Repositories
اعثر على أفضل المستودعات باستخدام الذكاء الاصطناعي.سنبحث عن أفضل المستودعات المطابقة باستخدام الذكاء الاصطناعي.
- rlinf/rlinf
RLinf/RLinf
2,502عرض على GitHubRLinf is a distributed reinforcement learning orchestrator and embodied AI training framework. It provides the infrastructure to train vision-language-action models and robotic policies using a combination of reinforcement learning and supervised fine-tuning. The system is designed for scaling workloads across GPU clusters, managing the placement of actors, rollout workers, and environment components. It features a specialized robotics data collection pipeline for gathering teleoperated demonstrations and simulation trajectories into standardized replay buffers, alongside a hardware interface
Reduces memory overhead and prevents catastrophic forgetting by freezing backbone parameters and updating only the output head.
Pythonagentic-aiembodied-aireinforcement-learning
