EntroPack: Fast and Accurate Entropy-Coded Weight Compression at Arbitrary Bitrates
cs.LG, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/modelscope/entropack
Sources
- HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models
- Asymmetric numeral systems: entropy coding combining speed of Huffman coding with compression rate of arithmetic coding
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- FP8 Formats for Deep Learning
- TorchAO: PyTorch-Native Training-to-Serving Model Optimization
- Float8@2bits: Entropy Coding Enables Data-Free Model Compression
- Approaching Shannon Bound with Lossless LLM Weight Compression
- Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks