glossary termAngestromTrust 60Published 3mo agoLive · 2mo ago
Quantization
Shrinking a model by storing its weights at lower precision.
Shrinking a model by storing its weights at lower precision. Shrinking a model by storing its weights at lower precision.
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownQuantBench →
- LinkedLinked via unknownQuantization at 1.58 bits →
- LinkedLinked via unknownHow Width and Data Shape Generalization Scaling Laws in Quadratic Neural Networks →
- LinkedLinked via unknownCondensing Large-Scale Datasets Directly with Minimal Information Loss →
- LinkedLinked via unknownGSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache →
- LinkedLinked via unknown$\text{Log}_\text{b}$Quant: Quantizing Language Models in Logarithmic Space →
- PossiblePossibly related (embedding) · 48%lucidrains/vector-quantize-pytorch →
- PossiblePossibly related (embedding) · 52%The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs →
Related to (incoming)
toolQuantBenchpaperQuantization at 1.58 bitspaperHow Width and Data Shape Generalization Scaling Laws in Quadratic Neural NetworkspaperCondensing Large-Scale Datasets Directly with Minimal Information LosspaperGSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cachepaper$\text{Log}_\text{b}$Quant: Quantizing Language Models in Logarithmic Spacerepolucidrains/vector-quantize-pytorchpaperThe Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMspaperSLORR: Simple and Efficient In-Training Low-Rank RegularizationpaperRequential Coding: Pushing the Limits of Model Compression with Self-Generated Training DatapaperKroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers
Covers (incoming)
Related across the graph
repolucidrains/vector-quantize-pytorchpaperKroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformersnews[R] Statistically-Lossless Quantization of Large Language ModelspaperQuantization at 1.58 bitspaperThe Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMspaperSLORR: Simple and Efficient In-Training Low-Rank Regularizationnews[Paper] Statistically-Lossless Quantization of Large Language ModelspaperHow Width and Data Shape Generalization Scaling Laws in Quadratic Neural NetworkspaperCondensing Large-Scale Datasets Directly with Minimal Information LosspaperRequential Coding: Pushing the Limits of Model Compression with Self-Generated Training DatapaperGSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV CachetoolQuantBenchpaper$\text{Log}_\text{b}$Quant: Quantizing Language Models in Logarithmic Space