Post #1651

Hugging Face (Twitter) RT @yukangchen_: We open-sourced QeRL — Quantization-enhanced Reinforcement Learning ! 🧠 4-bit quantized RL training 💪 Train a 32B LLM on a single H100 GPU ⚙️ 1.7× faster overall training 🎯 Accuracy on par with bfloat16-level accuracy 🔥 Supports NVFP4 quantization format Moreover, we show that quantization helps exploration in RL training. Paper: https://huggingface.co/papers/2510.11696 Code: github.com/NVlabs/QeRL #NVIDIA#AIResearch#ReinforcementLearning#Quantization#LLM#EfficientAI