Conrad Fernandez

llama.cpp

2 items with this tag.

  • Sep 23, 2026

    Module 5 — Placing the Experts

    • local-ai
    • moe
    • vram
    • llama.cpp
    • roofline
  • Sep 23, 2026

    Module 6 — Prefill vs. Decode

    • local-ai
    • moe
    • performance
    • llama.cpp

Created with Quartz v5.0.0 © 2026

  • GitHub
  • LinkedIn
  • Email