東's Projects
C++ NOTE :tm:
AIGC NOTE 系统性记录:从0到1 :alien:
The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.
CUDA NOTE :tm: :rocket:
NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models
纯c++的全平台llm加速库,支持python调用,chatglm-6B级模型单卡可达10000+token / s,支持glm, llama, moss基座,手机端流畅运行
视频编解码 NOTE :tm:
A new tensorrt integrate.
A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution, YUV2RGB, cuOSD,).
🛠 A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOv5, YOLOX, YOLOP, YOLOv6, YOLOR, MODNet, YOLOX, YOLOv7, YOLOv8. MNN, NCNN, TNN, ONNXRuntime.
手机端极致优化的高性能神经网络前向计算框架 ncnn :sparkles:
视频编解码: 硬解码多路高并发 CASE :tm: :currency_exchange:
C++ library based on tensorrt integration :100:
The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, WebAssembly
香橙派5-plus:RK3588 浅入门到深部署 :tm: :jack_o_lantern:
部署工程模板 :tm: :information_desk_person:
模型剪枝 随笔 :tm: :sparkles:
pybind11 — Seamless operability between C++11 and Python :city_sunrise:
模型量化 随笔 :tm: :fire:
Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
算能芯片部署优化demo
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
NVIDIA® TensorRT™ NOTE :tm: 学习记录以及相关理解 :rocket:
C++ library based on tensorrt integration
A simple tool that can generate TensorRT plugin code quickly.
The Triton Inference Server provides an optimized cloud and edge inferencing solution. :rocket:
Development repository for the Triton language and compiler