DEV Community

Performance

Tag for content related to software performance.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Porting a 1,200-line persistent CUDA megakernel to Qwen3-TTS: ~25 ms to first audio chunk

Porting a 1,200-line persistent CUDA megakernel to Qwen3-TTS: ~25 ms to first audio chunk

2
Comments
3 min read
SQLAlchemy Relationship Lazy Loading Strategies in Multi-Tenant FastAPI: N+1 Queries and the Cost of Joinedload

SQLAlchemy Relationship Lazy Loading Strategies in Multi-Tenant FastAPI: N+1 Queries and the Cost of Joinedload

1
Comments 1
4 min read
Elemetry data: Running 284B MoE at 0.00 GB Active VRAM

Elemetry data: Running 284B MoE at 0.00 GB Active VRAM

Comments
1 min read
Where does your startup time actually go?

Where does your startup time actually go?

Comments
4 min read
I benchmarked my own semantic cache against RedisVL and Upstash for a week. Here is what actually held up

I benchmarked my own semantic cache against RedisVL and Upstash for a week. Here is what actually held up

Comments
6 min read
SynaptoRoute v0.3.0: Matching Semantic Router While Scaling to 50,000 Routes

SynaptoRoute v0.3.0: Matching Semantic Router While Scaling to 50,000 Routes

Comments
5 min read
The 3-Second Rule of Web Performance — And How to Beat It

Master checklist plus CSS loading caveats

The 3-Second Rule of Web Performance — And How to Beat It

13
Comments 5
33 min read
Reality of L2 in ETH

Reality of L2 in ETH

Comments
7 min read
Why Chunking Matters in RAG: The Hidden Key to Better Retrieval

Why Chunking Matters in RAG: The Hidden Key to Better Retrieval

Comments
2 min read
The Magic of Branchless in FinTech: How to Tame the NASD 30/360 Financial Standard and Solve the IRR Equation Without a Single IF

The Magic of Branchless in FinTech: How to Tame the NASD 30/360 Financial Standard and Solve the IRR Equation Without a Single IF

2
Comments
10 min read
I found my own tool making twice the API calls it should. Here's what I fixed.

I found my own tool making twice the API calls it should. Here's what I fixed.

Comments
2 min read
KNN early termination in Manticore Search

KNN early termination in Manticore Search

Comments
8 min read
PostgreSQL query planner parameters and prepared statements

PostgreSQL query planner parameters and prepared statements

Comments 1
11 min read
Quick Diagnostic Commands for GBase 8a Cluster Glitches

Quick Diagnostic Commands for GBase 8a Cluster Glitches

2
Comments
2 min read
Optimizing Web Performance for Users on Mobile Data: Lessons from Building a Travel Tech Platform

Optimizing Web Performance for Users on Mobile Data: Lessons from Building a Travel Tech Platform

2
Comments
2 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.