deepseek-ai / DeepEP
DeepEP: an efficient expert-parallel communication library
See what the GitHub community is most excited about today.
DeepEP: an efficient expert-parallel communication library
Large Language Model Deployment Toolkit
FlashInfer: Kernel Library for LLM Serving
CUDA accelerated rasterization of gaussian splatting
Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models.
Causal depthwise conv1d in CUDA, with a PyTorch interface
CUDA Kernel Benchmarking Library
NCCL Tests
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.
cuVS - a library for vector search and clustering on the GPU
CUDA Library Samples
FlashMLA: Efficient MLA decoding kernels
[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.
RCCL Performance Benchmark Tests
Tile primitives for speedy kernels
Instant neural graphics primitives: lightning fast NeRF and more
LLM training in simple, raw C/CUDA
[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl