Quantization

Pushing Intelligence to 4-bit
Four-bit floating point is moving from a storage-only compression trick to a primitive for training and inference across LLMs, diffusion, video generation, KV cache, and attention.
Jun 16, 2026
Pushing Intelligence to 4-bit
Four-bit floating point is moving from a storage-only compression trick to a primitive for training and inference across LLMs, diffusion, video generation, KV cache, and attention.
Jun 16, 2026 1 min read
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
Diffusion models have been proven highly effective at generating high-quality images. However, as these models grow larger, they …
PDF Cite Code Project Video Demo Blog
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
FP8 training has emerged as a promising method for improving training efficiency. Existing frameworks accelerate training by applying …
PDF Cite Code Project Demo
COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training