jonmatumalpha
conceptsnotesexperimentsessays

© 2026 Jonatan Mata · alpha · v0.1.0

#performance

2 articles tagged #performance.

  • Inference Optimization

    Techniques to reduce cost, latency, and resources needed to run language models in production, from quantization to distributed serving.

    seed#inference#optimization#quantization#latency#serving#llm#performance
  • Server Components

    React paradigm where components execute on the server, sending only HTML to the client, reducing the JavaScript bundle and improving performance.

    seed#server-components#rsc#react#nextjs#performance#rendering
All tags