Gunjan Dhanuka — Learning Notes

training

2 items with this tag.

  • Sep 02, 2026

    NaViT Sequence Packing

    • vision-transformer
    • efficiency
    • training
    • variable-length
    • flashattention
  • Sep 02, 2026

    Recomputation (Activation Checkpointing)

    • gpu
    • recomputation
    • activation-checkpointing
    • memory
    • flashattention
    • training
    • mfu
    • llm-systems

Created with Quartz v5.0.0 © 2026

  • Personal site
  • Research
  • Field notes
  • Source