Skip to content
View jt-zhang's full-sized avatar

Highlights

  • Pro

Organizations

@thu-ml

Block or report jt-zhang

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
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.

  • 🚙 I enjoy self-driving and have traveled in [Chile, California, Qinghai, Yunnan, Ningxia, Inner Mongolia, Jiangsu, Hebei, Liaoning, Anhui, Shanxi, Zhejiang, Shanghai, and Beijing].

  • 📮 WeChat: Zjt_Tete

Pinned Loading

  1. thu-ml/SageAttention Public

    Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

    Cuda 965 59

95 contributions in the last year

Contribution Graph
Day of Week February March April May June July August September October November December January February
Sunday
Monday
Tuesday
Wednesday
Thursday
Friday
Saturday
Less
No contributions.
Low contributions.
Medium-low contributions.
Medium-high contributions.
High contributions.
More

Contribution activity

February 2025

Created 3 repositories

Created an issue in triton-lang/triton that received 2 comments

Dose Triton supports new features of Blackwell for RTX5090 and 5080?

I saw that Triton supports new features of Blackwell, but is it also compatible with RTX5090 and 5080?

2 comments
Opened 1 other issue in 1 repository
postechdblab/ASM 1 open
Loading

Seeing something unexpected? Take a look at the GitHub profile guide.