FlashInfer: Kernel Library for LLM Serving
Repository Index
132,241 visible repositories in the index
1–7 of 7 · Most stars
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
- attention
- inference-acceleration
- llm
- quantization
FlashKDA: high-performance Kimi Delta Attention kernels
Flash Attention in ~100 lines of CUDA (forward pass only)
cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
- attention
- blackwell
- cuda-kernels
- flash-attention
Additional utils and helpers to extend TensorFlow when build recommendation systems, contributed and maintained by SIG Recommenders.
- tensorflow-recommenders-addons
- sig-recommenders
- recommender-system
- tensorflow
reproducing the flapping airplanes megakernel, in collab with magni