deepseek-ai / DeepEP
DeepEP: an efficient expert-parallel communication library
See what the GitHub community is most excited about this month.
DeepEP: an efficient expert-parallel communication library
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.
CUDA accelerated rasterization of gaussian splatting
LLM training in simple, raw C/CUDA
CUDA Library Samples
FlashInfer: Kernel Library for LLM Serving
RCCL Performance Benchmark Tests
NCCL Tests
[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.
Distributed multigrid linear solver library on GPU
Tile primitives for speedy kernels
Instant neural graphics primitives: lightning fast NeRF and more
Lightning fast differentiable SSIM.
PyTorch bindings for CUTLASS grouped GEMM.
Causal depthwise conv1d in CUDA, with a PyTorch interface
CUDA Kernel Benchmarking Library
cuVS - a library for vector search and clustering on the GPU