flashinfer-ai / flashinfer
FlashInfer: Kernel Library for LLM Serving
See what the GitHub community is most excited about this week.
FlashInfer: Kernel Library for LLM Serving
DeepEP: an efficient expert-parallel communication library
[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.
Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
Tile primitives for speedy kernels
DeepGEMM: clean and efficient BLAS kernel library on GPU
LLM training in simple, raw C/CUDA
NCCL Tests
how to optimize some algorithm in cuda.
GPU accelerated decision optimization