jt-zhang

Follow

Jintao Zhang jt-zhang

Follow

A PhD student at Tsinghua University, focusing on efficient training and inference of large models.

345 followers · 67 following

@thu-ml, Tsinghua University
Beijing, China
https://jt-zhang.github.io/

Achievements

Achievements

Highlights

Pro

Organizations

jt-zhang/README.md

Hi 😊

I am a first-year PhD student in the CS Dept. at Tsinghua University, focusing on efficient training and inference of large models.

🏠 My Homepage.

WeChat ID : Zjt_Tete

Pinned Loading

thu-ml/TurboDiffusion thu-ml/TurboDiffusion Public

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Python 3.3k 224
thu-ml/SageAttention thu-ml/SageAttention Public

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

Cuda 3.1k 330
thu-ml/SpargeAttn thu-ml/SpargeAttn Public

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

Cuda 921 83
CardinalityEstimationTestbed CardinalityEstimationTestbed Public

CardinalityEstimationTestbed

Python 49 14
Sparse_Attention_API Sparse_Attention_API Public

Python 67 7
attention-survey/Efficient_Attention_Survey attention-survey/Efficient_Attention_Survey Public

A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention

278 5