Elijah's Notes

prefill

1 item with this tag.

  • May 25, 2025

    Transformer Architecture and Implementation

    • transformers
    • architecture
    • attention
    • gqa
    • kv-cache
    • flashattention
    • batching
    • prefill
    • decode
    • feedforward
    • normalization
    • machine-learning

Created with Quartz v5.0.0 © 2026

  • GitHub