← Developers
Open on GitHub 
#13393 71
Jintao Zhang
@jt-zhang · China
1.53k
Weighted score
194
Contributions
9
Repos
Top repos
- thu-ml/SageAttention
- thu-ml/SpargeAttn
- thu-ml/TurboDiffusion
- byungsoo-oh/ml-systems-papers
- AmberLJC/LLMSys-PaperList
- xlite-dev/Awesome-LLM-Inference
- OpenDataBox/awesome-data-llm
- showlab/Awesome-Video-Diffusion
- deepseek-ai/3FS
Ranked AI repos5
69432692
thu-ml/SageAttention
+0
[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.
3.97k· Cuda· Infrastructure
4056210
thu-ml/TurboDiffusion
+1
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
3.86k· Python· Infrastructure
80513399
AmberLJC/LLMSys-PaperList
+0
Large Language Model (LLM) Systems Paper List
2.29k· Python· Lists
10309232
thu-ml/SpargeAttn
+0
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
1.26k· Cuda· Infrastructure
14982594
byungsoo-oh/ml-systems-papers
+0
Curated collection of papers in machine learning systems
656· Lists