flashinfer-ai / flashinfer
FlashInfer: Kernel Library for LLM Serving
See what the GitHub community is most excited about today.
FlashInfer: Kernel Library for LLM Serving
Tile primitives for speedy kernels
GPU accelerated decision optimization
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without lossing end-to-end metrics across language, image, and video models.
CUDA accelerated rasterization of gaussian splatting
NCCL Tests
Causal depthwise conv1d in CUDA, with a PyTorch interface
DeepEP: an efficient expert-parallel communication library
CUDA Library Samples
Instant neural graphics primitives: lightning fast NeRF and more
LLM training in simple, raw C/CUDA
CUDA Kernel Benchmarking Library
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.
[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl