Jintao Zhang

Cascadia: An Efficient Cascade Serving System for Large Language Models

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention

UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers

Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency

SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference

Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity