DEV Community

Performance

Tag for content related to software performance.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Valkey 9.2's forkless BGSAVE cuts my memory spike from 350MB to 10MB

Valkey 9.2's forkless BGSAVE cuts my memory spike from 350MB to 10MB

6
Comments
7 min read
Rediscovering the Schwartzian Transform: Why I Had to Comment on a Flutter Performance Article

Rediscovering the Schwartzian Transform: Why I Had to Comment on a Flutter Performance Article

10
Comments
7 min read
A service mesh costs 0.16ms at one connection and 86% of your throughput at 32

A service mesh costs 0.16ms at one connection and 86% of your throughput at 32

12
Comments 1
6 min read
What Actually Happens During Speculative Decoding in LLMs

What Actually Happens During Speculative Decoding in LLMs

Comments
8 min read
I built a regex debugger that shows every backtrack (flame graph included)

I built a regex debugger that shows every backtrack (flame graph included)

Comments
3 min read
Rendering a 3D world in the browser is the easy part. Three.js gets you a spinning cube in ten minutes.

Rendering a 3D world in the browser is the easy part. Three.js gets you a spinning cube in ten minutes.

1
Comments 2
4 min read
Training a neural network on the GPU in pure PHP (and what kernel fusion did for it)

Training a neural network on the GPU in pure PHP (and what kernel fusion did for it)

Comments
3 min read
Vector Database Memory Sizing and Cost Math: How Much RAM Do 1 Million Vectors Need?

Vector Database Memory Sizing and Cost Math: How Much RAM Do 1 Million Vectors Need?

Comments
11 min read
FP16 Quantization Made Our In-Browser Real-ESRGAN 4.8x Faster — and Nearly Destroyed Our Inpainting Model

FP16 Quantization Made Our In-Browser Real-ESRGAN 4.8x Faster — and Nearly Destroyed Our Inpainting Model

Comments
6 min read
Database Connection Pooling: Why Opening a New Database Connection Every Time Is a Bad Idea

Database Connection Pooling: Why Opening a New Database Connection Every Time Is a Bad Idea

Comments
3 min read
Your system prompt is silently killing your prompt cache

Your system prompt is silently killing your prompt cache

Comments
5 min read
Benchmarking regex patterns properly: P95/P99, equivalence checks, real engines

Benchmarking regex patterns properly: P95/P99, equivalence checks, real engines

Comments
2 min read
Python 3.13 Free-Threading: What Actually Happens When the GIL Is Removed

Python 3.13 Free-Threading: What Actually Happens When the GIL Is Removed

Comments
5 min read
What Google's TurboQuant Does and Why It Actually Matters

What Google's TurboQuant Does and Why It Actually Matters

Comments
5 min read
Our cache TTL was shorter than the gap between reads, which makes it a timer, not a cache

Our cache TTL was shorter than the gap between reads, which makes it a timer, not a cache

Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.