Ever wondered why YouTube videos load instantly even in remote areas?
Image: Földhegy, CC BY-SA 3.0, via Wikimedia Commons
Ever wondered why YouTube videos load instantly even in remote areas?
Imagine you're in a remote village with slow internet, trying to watch a YouTube video.
A CDN stores popular videos closer to you, so your video loads faster even with a weak connection. The punchline is: CDN caches content at edge locations close to users.
Example
You watch a video in a remote village, and it loads instantly because it's stored nearby, not on the slow village server.
Remember this
A CDN speeds up content delivery by storing it closer to users.
Text adapted from Wikipedia, licensed under CC BY-SA 4.0.
Distributed hash table
Ever wondered how your favorite streaming service instantly starts playing a movie?
paged attention (vLLM) improves serving throughput
Paged attention (vLLM) improves serving throughput by reducing latency through non-contiguous KV-cache pages, enabling faster data retrieval
consistent hashing solves: minimizes key redistribution when servers are added/removed
Ever wonder why adding or removing servers doesn't mess up your favorite streaming service?
Triton auto-tunes BLOCK_SIZE: different sizes optimize for different hardware
Ever wondered why videos look different on various devices?
GQA reduces KV-cache memory by the group factor
Ever wondered how websites stay fresh in search results?
Glossary of poker terms
Ever hit a wall with your phone's search?
Swipe through 100 ML concepts daily
Open Pocket Polymath