Log inSign up
Pavan Jayasinha
565 posts
user avatar
Pavan Jayasinha
@pavanjayasinha
ECE @UWaterloo // prev: quant research @citsecurities, gpu perf @Modular, ASICs @extropic_ai + @UntetherAI, neutral atom QC @QuantumIQC
E7 4417
pavanjay.com
Joined February 2017
473
Following
2,983
Followers

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • Pinned
    user avatar
    Pavan Jayasinha
    @pavanjayasinha
    May 4, 2025
    I implemented an LLM end-to-end in hardware, and ran it on an FPGA. Zero Python. Zero CUDA. Just pure SysVerilog. All my progress + everything I learned from 200h of LLM chip design (demo at the end)👇
    348K
  • user avatar
    Pavan Jayasinha
    @pavanjayasinha
    Sep 5, 2024
    Got nerd-sniped into robotics research 2 months ago with no prior experience Ended up reimplementing computer vision on my Roomba with SLAM and now it's mapping the lab like a mini-explorer Here are my 3 most surprising takeaways:
    00:00
    179K
  • user avatar
    Pavan Jayasinha
    @pavanjayasinha
    May 27, 2025
    I got carried away trying to implement radix sort in CUDA today. Ended up getting to ~0.42 billion elements sorted per sec on GH200 - not terrible for a price of 130 lines of code. Code for the cuda curious: (and other jobless Canadians on Mem Day) github.com/Sinestro38/gpu…
    32K
  • user avatar
    Pavan Jayasinha
    @pavanjayasinha
    Sep 5, 2024
    Replying to @pavanjayasinha
    #1 - Many tasks in robotics are better done without ML Coming from a software/ML background, I asked myself why traditional robotics hasn't been replaced with ML. I learned that ML often comes at the cost of speed & predictability over many traditional statistical approaches.
    https://ykulbashian.medium.com/no-time-for-ml-be461bcfe063
    8.6K
  • user avatar
    Pavan Jayasinha
    @pavanjayasinha
    May 17, 2024
    Just soldered my first custom pcb, I get why we outsource this to sweat shops across the ocean now 😂
    14K
  • user avatar
    Pavan Jayasinha
    @pavanjayasinha
    May 4, 2025
    Replying to @pavanjayasinha
    Before we dive into the project log, some context: I made this as part of a lab project for the most cracked course at Waterloo: ECE 327. Nachiket Kapre (the Prof) designed this lab. Because of it, I went from knowing ZERO Verilog to now squashing delta‑cycle races caused by #0
    15K
  • user avatar
    Pavan Jayasinha
    @pavanjayasinha
    May 4, 2025
    Replying to @pavanjayasinha
    Finally, here's the culmination of this lab project - feeding a prompt into the I-BERT model deployed natively on the FPGA running tokens in, tokens out!
    8.9K
  • user avatar
    Pavan Jayasinha
    @pavanjayasinha
    Sep 5, 2024
    Replying to @pavanjayasinha
    #3 - You learn much more by debugging and trying to figure shit out than following a course The main difficulty in this project was surprisingly a network issue through docker and navigating a complex build system. None of these are taught in ROS courses. ...
    6.1K
  • user avatar
    Pavan Jayasinha
    @pavanjayasinha
    Sep 16, 2024
    New side quest acquired: dethrone nvidia’s cuBLAS 🫡 Time to help cook Mojo on GPU @Modular this Fall🏃
    7.7K
  • user avatar
    Pavan Jayasinha
    @pavanjayasinha
    Sep 5, 2024
    Replying to @pavanjayasinha
    I'd highly recommend playing around with robotics - think of an easy project in actuation/perception/control and take the first step. I'm very bullish on humanoid robotics, and psyched to play around with more robotics stuff when I'm back in the loo post-coop 🥘
    6.1K
  • user avatar
    Pavan Jayasinha
    @pavanjayasinha
    Sep 5, 2024
    Replying to @pavanjayasinha
    I did 3 out of a 22-hour ROS course (theconstruct.ai) and just jumped into porting the SLAM codebase I was given to ROS2. It takes much less time to get started than I thought.
    The Construct: Where Your Robotics Career Happens
    From theconstruct.ai
    7.4K
  • user avatar
    Pavan Jayasinha
    @pavanjayasinha
    Sep 5, 2024
    Replying to @pavanjayasinha
    #2 - ROS[2] makes robot SW a lot more fun To get this to work, I had to convert an existing SLAM algo developed by Kevin Hu (VIP Lab) here at UWaterloo to ROS2. It made me realize how much of the grunt work ROS2 alleviates from someone just trying to ship a robotics project.
    Turtlebot4, the roomba type robot I used
    8.9K
  • user avatar
    Pavan Jayasinha
    @pavanjayasinha
    May 4, 2025
    Replying to @pavanjayasinha
    Phase 0: Learning system verilog To implement anything in hw, you need to know a hardware description language (HDL). Since the course used system verilog, I got cracking on hdlbits.01xz.net Hdlbits taught me the core syntax & structure of verilog: • What is a module
    14K
  • user avatar
    Pavan Jayasinha
    @pavanjayasinha
    May 21, 2021
    So grateful to be starting a new chapter of growth at @ZapataComputing in late June. I'll be working as an Intern in @aperdomoortiz team. I'm excited to learn so much about QML as well as help out with Zapata's efforts to build meaningful quantum-enabling software.