FlashInfer: Kernel Library for LLM Serving
Repository Index
100,822 visible repositories in the index
1–6 of 6 · Most stars
Tile primitives for speedy kernels
GPU Accelerated t-SNE for CUDA with Python bindings
FlashKDA: high-performance Kimi Delta Attention kernels
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
- ai-infra
- attention
- inference-acceleration
- llm
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
- anns
- building-blocks
- clustering
- cuda