Keyvhinng Espinoza
@keyvhinng.bsky.social
Software Engineer 👨💻 - Performance, Scalability, Distributed Systems
If you want to learn vLLM under the hood, this is the post www.aleksagordic.com/blog/vllm
Inside vLLM: Anatomy of a High-Throughput LLM Inference System - Aleksa Gordić
From paged attention, continuous batching, prefix caching, specdec, etc. to multi-GPU, multi-node dynamic serving at scale.
aleksagordic.com
Excellent presentation from @tigerbeetle.com with brilliant insights: 'Those who would trade safety for performance deserve neither safety nor performance.' www.youtube.com/watch?v=yKgf...
1000x: The Power of an Interface for Performance by Joran Dirk Greef
YouTube video by TigerBeetle
youtube.com
The MemoryDB paper shows the power of separating responsibilities through clever composition. I think this DB frontend/execution plus a distributed transaction log pattern can be promising for creating serverless variants of many popular databases. E.g., Aurora adopts a similar decoupling approach.
Node.js now supports TypeScript. Here's everything you need to know: www.totaltypescript.com/typescript-i...
Node.js Now Supports TypeScript By Default
TypeScript is coming to Node 23. Let's break down what that means.
totaltypescript.com
Even if you are not deep into AI, this talk by Ilya offers incredible insights into the cutting edge of AI capabilities and what the future holds www.youtube.com/watch?v=1yvB...
Ilya Sutskever: "Sequence to sequence learning with neural networks: what a decade"
YouTube video by seremot
youtube.com
Using the Advent of Code to improve my Rust skills. This is the way ⭐⭐