Gunjan Dhanuka — Learning Notes

sparse-attention

8 items with this tag.

  • Sep 14, 2026

    DSA (DeepSeek Sparse Attention)

    • attention
    • sparse-attention
    • dsa
    • csa
    • deepseek
    • trainable-sparse
    • lightning-indexer
    • top-k
    • mla
    • long-context
    • kv-cache
  • Sep 14, 2026

    MoBA (Mixture of Block Attention)

    • attention
    • sparse-attention
    • moba
    • moonshot
    • kimi
    • block-sparse
    • top-k
    • mixture-of-experts
    • long-context
    • trainable-sparse
  • Sep 12, 2026

    QSA (Qwen Sparse Attention)

    • attention
    • sparse-attention
    • qsa
    • qwen
    • trainable-sparse
    • block-selection
    • indexer
    • compression
    • long-context
    • deepseek
  • Sep 12, 2026

    On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability

    • qwen
    • alibaba
    • qsa
    • gated-deltanet
    • sparse-attention
    • hybrid
    • moe
    • muon
    • long-context
    • deepseek
    • n-gram
  • Sep 11, 2026

    Learn: SOTA Attention Synthesis (Sept 2026)

    • attention
    • sota
    • synthesis
    • frontier
    • rope
    • gqa
    • mla
    • flashattention
    • nsa
    • sparse-attention
    • ssm
    • hybrids
    • multimodal
    • capstone
    • transformers
  • Sep 10, 2026

    Sliding-Window Attention

    • attention
    • sparse-attention
    • sliding-window
    • local-attention
    • mistral
    • long-context
    • receptive-field
    • kv-cache
  • Sep 10, 2026

    Sparse Attention

    • attention
    • sparse-attention
    • longformer
    • bigbird
    • global-tokens
    • dilation
    • random-attention
    • long-context
  • Sep 10, 2026

    Learn: Sparse & Sliding-Window Attention

    • attention
    • transformers
    • sparse-attention
    • sliding-window
    • longformer
    • bigbird
    • attention-sinks
    • streaming
    • long-context
    • flops

Created with Quartz v5.0.0 © 2026

  • Personal site
  • Research
  • Field notes
  • Source