MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization Paper • 2602.03537 • Published 26 days ago • 3
DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers Paper • 2602.02016 • Published 27 days ago • 12
Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation Paper • 2601.22813 • Published about 1 month ago • 57
tencent/HunyuanImage-3.0-Instruct-Distil Image-to-Image • 83B • Updated 26 days ago • 943 • 50
WUSH: Near-Optimal Adaptive Transforms for LLM Quantization Paper • 2512.00956 • Published Nov 30, 2025 • 23
TiDAR: Think in Diffusion, Talk in Autoregression Paper • 2511.08923 • Published Nov 12, 2025 • 128
view article Article A Review on the Evolvement of Load Balancing Strategy in MoE LLMs: Pitfalls and Lessons Feb 4, 2025 • 30
Running on CPU Upgrade Featured 3.02k The Smol Training Playbook 📚 3.02k The secrets to building world-class LLMs