ashvardanian
Joined 5 years ago
Karma
4,506
Submissions
833
Member since
Nov 26
Recent submissions
Comment · 1 month ago
One fairly revealing microbenchmark for WASM runtimes is `int8` dot products & angular/cosine distances.
(My) NumKong [1] has implementations targeting both vanilla AVX2/Haswell and AVX2-VNNI/Alder Lake, which makes it easy to see where runtimes and code generators leave performance on the table.
I started a few Wasmtime/Cranelift PRs around this, but didn’t manage to finish them :facepalm: Might be a fun weekend project for someone interested in backend/codegen work.
Comment · 2 months ago
If only we had a myriad of heavily funded, founder-led AI-for-coding startups that could afford to store a few source files and need all that code for training anyway :)
PS: Saw Cursor’s Origin announcement a second later.
Comment · 4 months ago
Got really excited for this model and asked my Opus planners in 3 pretty different projects to use Sonnets instead of Opus subagents to help me experiment on HPC kernels faster. Not one of them ended up writing a single line of code... Sonnets just kept spinning, wasting tokens. Can't remember the last time it happened with Opus in my codebases. Reverting back.
Comment · 5 months ago
I really like the speed at which Cloudflare is executing toward becoming a critical infrastructure player with all of those new product offerings. That said, not everything needs to be serverless. Their Gen 13 hardware looks impressive, and it’s a pity you can’t rent it by the hour like AWS EC2 Metal instances.
<ashvardanian.com>
<github.com/ashvardanian>