Hacker News: bertaye

New comment by bertaye in "Show HN: Agentic CUDA Kernel Optimizer"

bertaye — Fri, 25 Sep 2026 17:15:41 +0000

It cant if you be cautious about it because the inputs can set manually and outputs are generated through the cuda harness by executing the reference kernel, again can be provided externally.

Comparison is simply byte by byte equalness check of reference kernel outputs with candidate (optimized) outputs.

Why I added ai generated inputs then? I was just being lazy and this was more of a langgraph playground for me:)

New comment by bertaye in "Show HN: Agentic CUDA Kernel Optimizer"

bertaye — Fri, 25 Sep 2026 17:11:43 +0000

Hello, indeed you can just use that.

The basic idea here is just automating and limiting the steps that AI can take. These are described as ‘nodes’ and their actions are limited/more descriptive from developer perspective.

The langgraph simply allows you to set some fences around the AI agent for a goal, instead of raw terminal flow. Is it better? Arguable.

New comment by bertaye in "Show HN: Agentic CUDA Kernel Optimizer"

bertaye — Fri, 25 Sep 2026 14:16:37 +0000

honestly I know it exists but I never used it so can't compare

New comment by bertaye in "Show HN: Agentic CUDA Kernel Optimizer"

bertaye — Fri, 25 Sep 2026 14:15:06 +0000

That is the funny part actually; we can either provide a reference kernel + input cases for correctness check. In this case at first it will use test harness to run reference kernel with reference inputs ad save the outputs as ground truth. Or we can let AI to create a very basic reference implementation and input cases :D for my own experiments I used second one.

Show HN: Agentic CUDA Kernel Optimizer

bertaye — Fri, 25 Sep 2026 10:32:58 +0000

Hello; I was working on optimizing some CUDA kernels and I thought may be it is a good oppurtunity learn langgraph as well. I created a simple C++ CUDA Test Harness and handed that to AI agents. They can run kernels, get benchmarks, and even can profile via nsight

Comments URL: https://news.ycombinator.com/item?id=49842596

Points: 37

# Comments: 11

Show HN: WiFi-LLM

bertaye — Tue, 21 Jul 2026 13:32:07 +0000

Hello, while I was learning LLM Inference basics I realized with few tricks I could use my ESP32 for inference if I stream the weights only when they are needed from a host over WiFi.

Speed? Really bad. Lol. But this is just a technical demo of how it can be done. I really enjoyed while coding it. It has a sliding window which allows infinite generation ( of course meaningless :) )

Hope you will enjoy!

Comments URL: https://news.ycombinator.com/item?id=48992123

Points: 2

# Comments: 0