KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers
Post-training quantization (PTQ) of diffusion transformers (DiTs) to W4A4 severely degrades output quality, because activations entering each linear layer contain outliers that 4-bit formats cannot represent. The standard fix applies an invertible linear transform to the activations and its inverse to the weights before quantizing both. Normalization layers between blocks force this transform to run online at every denoising step, making its inference computation cost the binding design constraint. Existing options trade quantization quality for inference cost: per-channel scaling (SmoothQuant
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-xl-base-1.0 →
“Fuzzy title match (0.73): “KroQuant: Kronecker-Structured Block Transforms for Efficien” ≈ “stabilityai/stable-diffusion-xl-base-1.0””
- FuzzySimilar title/name (fuzzy) · 59%CompVis/stable-diffusion-v1-4 →
“Fuzzy title match (0.73): “KroQuant: Kronecker-Structured Block Transforms for Efficien” ≈ “CompVis/stable-diffusion-v1-4””
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-3.5-large →
“Fuzzy title match (0.73): “KroQuant: Kronecker-Structured Block Transforms for Efficien” ≈ “stabilityai/stable-diffusion-3.5-large””
- PossiblePossibly related (embedding) · 52%QuantBench →
- PossiblePossibly related (embedding) · 51%Bringing Nunchaku 4-bit Diffusion Inference to Diffusers →
- PossiblePossibly related (embedding) · 51%Quantization →
- FuzzySimilar title/name (fuzzy) · 87%lucidrains/x-transformers →
“Fuzzy title match (0.94): “KroQuant: Kronecker-Structured Block Transforms for Efficien” ≈ “lucidrains/x-transformers””
- FuzzySimilar title/name (fuzzy) · 84%huggingface/transformers →
“Fuzzy title match (0.92): “KroQuant: Kronecker-Structured Block Transforms for Efficien” ≈ “huggingface/transformers””
