LazyWeights: Decode-on-Demand Edge LLMs
cs.LG, cs.AR, cs.CL, cs.IT, math.IT
Submitted: 2026-11-12
Updated: 2026-11-18
Code: https://github.com/ggml-org/llama.cpp
Terminology
Sources
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference
- Asymmetric numeral systems: entropy coding combining speed of Huffman coding with compression rate of arithmetic coding
- APack: Off-Chip, Lossless Data Compression for Efficient Deep Learning 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