Gunjan Dhanuka — Learning Notes

uptraining

1 item with this tag.

  • Sep 10, 2026

    GQA / MQA (Grouped & Multi-Query Attention)

    • attention
    • kv-cache
    • gqa
    • mqa
    • inference
    • uptraining
    • llama
    • long-context

Created with Quartz v5.0.0 © 2026

  • Personal site
  • Research
  • Field notes
  • Source