vishal-padia
- Karma
- 0
- Created
- ()
- Submissions
- 0
- Show HN: Where a hand-written GPU kernel beats the library, and where it can't (kyrieblunders.bearblog.dev)
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…
- I made a kernel 2.2x faster. It made my training loop 3x slower (kyrieblunders.bearblog.dev)
- Wrote FA2 using CuteDSL, what worked and what didn't work (kyrieblunders.bearblog.dev)