News for hackers. Stuff that matters.

vishal-padia

Show HN: Where a hand-written GPU kernel beats the library, and where it can't

https://kyrieblunders.bearblog.dev/the-kernels-that-were-there/

I've been building streaming inference kernels for Zonos, the open SSM-based (Mamba2) TTS model, on an A10G. This post is two hand-written CuTeDSL kernels in two regimes, and the contrast is the point.The first is a skinny bf16 GEMV for the batch-1 decode projections. It beats cuBLAS by up to 1.36x, not because it's clever, but because cuBLAS pads the tiny M dimension out to a...

( Read More... | no comments | on HN )
Re:Ask HN: What Are You Working On? (June 2025) on Tuesday July 01, 2025 @09:00AM (#44433487)
working on local first, bloat free MLOps tool https://github.com/Vishal-Padia/tracely

it's still wip

Re:How I write code using Cursor: A review on Tuesday October 29, 2024 @06:26AM (#41982146)
yes this!!! Whenever I write a prompt, I tend to divide it into smaller prompts, and in this process, my brain thinks of multiple ways to solve the problem. So yes, it's not limiting my thought process. I didn't notice this thing until I read this.
Re:How I write code using Cursor: A review on Tuesday October 29, 2024 @06:20AM (#41982075)
I don't agree, in the initial stages solving problems without LLMs will give a good enough knowledge about the intricacies involved and it helps develop a structured approach while solving a problem!
Re:How I write code using Cursor: A review on Tuesday October 29, 2024 @01:34AM (#41979686)
In the article, you mentioned that you've been writing code for 36 years, so don't you feel IDEs like cursor make you feel less competent? Meaning I loved the process of scratching my head over a problem and then coming to a solution but now we have AI Agents solving the problems and optimizing code which takes the fun out of it.