sparse-attention

Open repos and models their makers tagged sparse-attention, most starred first. The same for everyone.

Images and videoRepo

ComfyUI-sol-attn

NVIDIA Sol-Attn for ComfyUI / Triton kernel on SM89 - SM121, with zero-copy MiniMax H3 nodes: memory-efficient attention, scheduled tau with graph preview, and feed-forward chunking. Measured 1.14–1.44× vs SageAttention and −37% MLP peak VRAM on H3

  • 161
  • Python
  • Apache-2.0
  • 3 mo ago
Saganaki22Take it
AI on my own machineRepo

aarambh-studio

🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained MoE, native video/document understanding, long-horizon tool agents, quantization-aware training. Scales: Tiny (25M) to Large (1.3B).

  • 112
  • Rust
  • Apache-2.0
  • 3 mo ago
AI on my own machineRepo

laptop-llm-cn

前沿 LLM 中文代码教材:KDA、AttnRes、MSA、mHC、Engram、MTP、Muon、Agent RL、多教师蒸馏、FP4 与本地 Serving · 18 章课程 · 无需云资源

  • 0
  • Python
  • MIT
  • 7 wk ago
Search GitHub and Hugging Face for sparse-attention

Get , open it once and sign in. Then come back here and press the button again.