caoxiang520

caoxiang520's Stars

• angry-crab/cudla_dev

  Language:C++5

• ifromeast/cuda_learning

  learning how CUDA works

  Language:Cuda18323

• leimao/CUDA-GEMM-Optimization

  CUDA Matrix Multiplication Optimization

  Language:Cuda14914

• luliyucoordinate/CUDA-GEMM-Optimization

  CUDA Matrix Multiplication Optimization

  Language:Cuda1

• luliyucoordinate/cute-flash-attention

  Implement Flash Attention using Cute.

  Language:Cuda642

• tmlfrkn/CUDAIntegratedTransformerTool

  Language:C++1

• vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Language:Python33.2k5k

• bytedance/lightseq

  LightSeq: A High Performance Library for Sequence Processing and Generation

  Language:C++3.2k329

• megvii-research/MOTRv2

  [CVPR2023] MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

  Language:Python39248

• megvii-research/MOTR

  [ECCV2022] MOTR: End-to-End Multiple-Object Tracking with TRansformer

  Language:Python64795

• ZikangZhou/HiVT

  [CVPR 2022] HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction

  Language:Python660126

• OpenDriveLab/UniAD

  [CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving

  Language:Python3.7k420

• zjhellofss/KuiperInfer

  校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step

  Language:C++2.7k302

• zjhellofss/KuiperLLama

  校招、秋招、春招、实习好项目，带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。

  Language:C++25760

• flashinfer-ai/flashinfer

  FlashInfer: Kernel Library for LLM Serving

  Language:Cuda1.7k169

• bytedance/byteir

  A model compilation solution for various hardware

  Language:MLIR39343

• InfiniTensor/InfiniTensor

  Language:C++18530

• Oneflow-Inc/trt_flash_attention

  Language:C++41

• Oneflow-Inc/flash-attention-v2

  Fast and memory-efficient exact attention

  Language:Python2

• NVIDIA/FasterTransformer

  Transformer related optimization, including BERT, GPT

  Language:C++6k896

• linClubs/BEVDet-ROS-TensorRT

  BEVDet online real-time inference using CUDA, TensorRT, ROS1 & C++.

  Language:C++9323

• maggiez0138/Swin-Transformer-TensorRT

  This project aims to explore the deployment of Swin-Transformer based on TensorRT, including the test results of FP16 and INT8.

  Language:Python16329

• OpenPPL/ppl.nn

  A primitive library for neural network

  Language:C++1.3k217

• owenliang/pytorch-transformer

  pytorch复现transformer

  Language:Python6823

• awagner8/Kvcache

  Language:Python1

• laugh12321/TensorRT-YOLO

  TensorRT-YOLO: A high-performance, easy-to-use YOLO deployment toolkit for NVIDIA, powered by TensorRT plugins and CUDA Graph, supporting C++ and Python.

  Language:C++88895

• ShaYeBuHui01/flash_attention_inference

  Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.

  1417

• chainyo/transformers-pipeline-onnx

  How to export Hugging Face's 🤗 NLP Transformers models to ONNX and use the exported model with the appropriate Transformers pipeline.

  Language:Jupyter Notebook24

• 66RING/tiny-flash-attention

  flash attention tutorial written in python, triton, cuda, cutlass

  Language:Cuda23821

• Oneflow-Inc/flash-attention

  Fast and memory-efficient exact attention

  Language:C++51