Optimizing a WebGPU Matmul Kernel for 1 TFLOP(zanussbaum.substack.com)

163 points by zanussbaum 1 year ago | 68 comments

Optimizing a Rust GPU matmul kernel(rust-gpu.github.io)

82 points by lukastyrychtr 1 year ago | 7 comments

Matrix Multiplications on GPUs Run Faster When Given “Predictable” Data (2024)(thonking.ai)

159 points by tosh 5 months ago | 46 comments

Making a parallel Rust workload 10x faster with (or without) Rayon(gendignoux.com)

105 points by lukastyrychtr 1 year ago | 28 comments

100k TPS over a billion rows: the unreasonable effectiveness of SQLite(andersmurphy.com)

344 points by speckx 10 months ago | 124 comments

Blog post by Anders Murphy benchmarking SQLite at 100k transactions per second over a billion rows, arguing its embedded single-writer design helps it scale.

Show HN: I trained a 9M speech model to fix my Mandarin tones(simedw.com)

426 points by simedw 8 months ago | 128 comments

Blog post describing a 9M-parameter Conformer-CTC model trained on ~300 hours of speech that grades Mandarin pronunciation and tones in the browser.