Skip to content
View Concyclics's full-sized avatar
51 followers · 113 following
  • National University of Singapore
  • Singapore
  • 05:55 (UTC +08:00)

Achievements

Achievement: QuickdrawAchievement: Pull Shark

Achievements

Achievement: QuickdrawAchievement: Pull Shark

Highlights

  • Pro

Block or report Concyclics

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
Concyclics/README.md

Hello 👋

I'm a first year CS PhD student in National University of Singapore supervised by Prof. HE Bingsheng. I will focus on mlsys to speedup LLM inference. Before this my previous works focus on high performance computing, including LAPACK subroutine optimization, LLM inference optimization and high throughput encryption algorithm design. I've also won a silver medal in ICPC and a bronze medal in the ICPC East Continental Final. For more details, you are welcome to have a view of my CV here.

You can find me by:

Rock's github stats

Pinned Loading

  1. LogQuantKV LogQuantKV Public

    LogQuantKV, a high precision 2-bit Quantization method

    Jupyter Notebook 12

  2. BiliBiliFollowSpider BiliBiliFollowSpider Public

    B站爬虫

    Jupyter Notebook 14 3

  3. nviennot/core-to-core-latency nviennot/core-to-core-latency Public

    Measures the latency between CPU cores

    Jupyter Notebook 1.2k 91

  4. pigirons/cpufp pigirons/cpufp Public

    A CPU tool for benchmarking the peak of floating points

    Assembly 548 131

  5. HiAE HiAE Public

    Official implementation of paper "HiAE: A High-Throughput Authenticated Encryption Algorithm for Cross-Platfor Efficiency"

    HTML 12

  6. AvxToNeon AvxToNeon Public

    Forked from kunpengcompute/AvxToNeon

    Encapsulate the frequently used AVX instructions as independent modules to reduce repeated development workload.

    C 3