MINE: Entropy-coded Memory-efficient Inference for Large Language Models
cs.LG, cs.DC, cs.PF
Submitted: 2026-11-06
Updated: 2026-11-09
Code: https://github.com/ggml-org/llama
Project page: https://dropbox.github.io/hqq_blog
Terminology
Sources
- SignRoundV2: Toward Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs
- Asymmetric numeral systems: entropy coding combining speed of Huffman coding with compression rate of arithmetic coding
- The Llama 3 Herd of Models
- NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks
- The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
- FP8 Formats for Deep Learning
- Pretraining Large Language Models with NVFP4
- Float8@2bits: Entropy Coding Enables Data-Free Model Compression
- Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis