Qingrenn / mmdeploy-summer-campLinks
🐱 ncnn int8 模型量化评估
☆13Updated 2 years ago
Alternatives and similar repositories for mmdeploy-summer-camp
Users that are interested in mmdeploy-summer-camp are comparing it to the libraries listed below
Sorting:
- A set of examples around MegEngine☆31Updated last year
- A tool convert TensorRT engine/plan to a fake onnx☆40Updated 2 years ago
- An onnx-based quantitation tool.☆71Updated last year
- ffmpeg+cuvid+tensorrt+multicamera☆12Updated 6 months ago
- TensorRT 2022 亚军方案,tensorrt加速mobilevit模型☆68Updated 3 years ago
- Quantize yolov7 using pytorch_quantization.🚀🚀🚀☆10Updated last year
- Quantize yolov5 using pytorch_quantization.🚀🚀🚀☆14Updated last year
- NVIDIA TensorRT Hackathon 2023复赛 选题:通义千问Qwen-7B用TensorRT-LLM模型搭建及优化☆42Updated last year
- ☆47Updated 2 years ago
- OneFlow->ONNX☆43Updated 2 years ago
- ☆22Updated last year
- For 2022 Nvidia Hackathon☆21Updated 3 years ago
- MegEngine到其他框架的转换器☆70Updated 2 years ago
- 该代码与B站上的视频 https://www.bilibili.com/video/BV18L41197Uz/?spm_id_from=333.788&vd_source=eefa4b6e337f16d87d87c2c357db8ca7 相关联。☆69Updated last year
- ☆26Updated last year
- https://start.oneflow.org/oneflow-yolo-doc☆22Updated 2 years ago
- TensorRT 2022复赛方案: 首个基于Transformer的图像重建模型MST++的TensorRT模型推断优化☆139Updated 3 years ago
- 分别使用OpenCV、ONNXRuntime部署CenterNet目标检测,包含C++和Python两个版本的程序☆9Updated 2 years ago
- HunyuanDiT with TensorRT and libtorch☆17Updated last year
- Awesome code, projects, books, etc. related to CUDA☆19Updated this week
- YOLOP with ONNXRuntime C++/MNN/TNN/NCNN☆9Updated 3 years ago
- https://zhuanlan.zhihu.com/p/577195854☆42Updated 2 years ago
- A GLCC Server for MMDeploy☆19Updated last year
- 车道线检测Lanenet TensorRT加速C++实现☆22Updated 3 years ago
- Quick and Self-Contained TensorRT Custom Plugin Implementation and Integration☆65Updated last month
- ☆42Updated 3 years ago
- DETR tensor去除推理过程无用辅助头+fp16部署再次加速+解决转tensorrt 输出全为0问题的新方法。☆12Updated last year
- Trans different platform's network to International Representation(IR)☆44Updated 7 years ago
- ☆17Updated last year
- Flash Attention in ~100 lines of CUDA (forward pass only)☆10Updated last year