How I Made CosyVoice3 2.2× Faster on Apple Silicon
How I bounded PyTorch MPS memory growth, cut CosyVoice3 latency below real time, and moved only the dispatch-bound LLM stage to MLX.
Tag archive
Notes connected by the Performance tag.
How I bounded PyTorch MPS memory growth, cut CosyVoice3 latency below real time, and moved only the dispatch-bound LLM stage to MLX.
Build a constrained KVM guest, run the AuthOS SQLite workload from the host, collect comparable results, and select a load for a longer test.
AuthOS appeared to hit SQLite's limits at 130 requests per second. Moving Argon2 work, audit writes, activity updates, and overload control changed the result—and exposed what …
I rebuilt the AuthOS SQLite benchmark, untangled two limits outside the database, and measured its useful operating point inside a budget-shaped VM.
You have a responsibility as a web developer to improve user experience. Improve performance and user experience by improving how you handle these few things.
In this short piece, I want to share how you can make a website that performs well for users. Speed is very essential.
Hugo is amazing for blazing fast static site generation. I felt that I should extend that by enabling PWA and adding self hosted comments to avoid Disqus. Here is how that …
No entries are filed here yet.
Browse all notes →