Pinned Loading

1. PCEngine PCEngine Public

   [MLSys'23] Exploiting Hardware Utilization and Adaptive Dataflow for Efficient Sparse Convolution in 3D Point Clouds.

   Cuda 11

2. dgSPARSE/dgSPARSE-Lib dgSPARSE/dgSPARSE-Lib Public

   PyTorch-Based Fast and Efficient Processing for Various Machine Learning Applications with Diverse Sparsity

   Cuda 120 28

3. infinigence/FlashOverlap infinigence/FlashOverlap Public

   A lightweight design for computation-communication overlap.

   Python 213 10

4. jamescsq47/PAROAtten jamescsq47/PAROAtten Public

   PAROAttn based on SAGEAttn

   Cuda 9 1

5. infinigence/Semi-PD infinigence/Semi-PD Public

   A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.

   Python 123 15

6. thu-nics/db-SP thu-nics/db-SP Public

   This repository contains the official implementation of db-SP, a sparsity-aware sequence parallelism strategy designed to accelerate sparse attention in visual generative models (e.g., Diffusion Tr…

   Python 2 1