Open Source Radar

Topic: sparse-attention

← Back to the radar

CategoriesAgents MCP Coding agents LLM RAG Inference Vector DBs Browser Workflows topic: sparse-attention ✕

SortTrending Most stars Newest2 repos · page 1/1

thu-ml/

SpargeAttn

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

1.0k98Cudaquiet

AarambhDevHub/

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).

6117Rustnew