Towards Full Pipeline FP8 Reinforcement Learning for LLMs
VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention
1
Attention Quantization for Tabular Foundation Models
1
DeepSeek v4.1 Flash Uncensored
1
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search
1
Training a 3.8B LLM to 0.384 CORE for $998 – Hugo Vergnes
15 min1
dealignai/GLM-5.3-CYBERSECURITY-FP8 — new model trending #13 on Hugging Face
5 min1