DataXujing / Bert_TensorRTLinks
Bert TensorRT模型加速部署
☆10Updated 3 years ago
Alternatives and similar repositories for Bert_TensorRT
Users that are interested in Bert_TensorRT are comparing it to the libraries listed below
Sorting:
- 国内外数据竞赛资讯整理☆18Updated 3 years ago
- 天池 NVIDIA TensorRT Hackathon 2023 —— 生成式AI模型优化赛 初赛第三名方案☆50Updated 2 years ago
- NVIDIA TensorRT Hackathon 2023复赛选题：通义千问Qwen-7B用TensorRT-LLM模型搭建及优化☆43Updated 2 years ago
- 大模型API性能指标比较 - 深入分析TTFT、TPS等关键指标☆19Updated last year
- 纯Python实现的深度学习框架，帮助你理解底层细节斩获offer☆21Updated 3 years ago
- 陆续开源医疗行业的深度学习模型及数据集☆13Updated 3 years ago
- deploy onnx models with TensorRT and LibTorch☆19Updated 3 years ago
- cpp rotation album，基于cpp eigen实现的3d旋转相册，GAMES101复现内容☆12Updated 3 years ago
- Whisper in TensorRT-LLM☆16Updated 2 years ago
- 使用DBNet检测条形码，包含C++和Python两种版本的程序☆37Updated 4 years ago
- A tool convert TensorRT engine/plan to a fake onnx☆41Updated 2 years ago
- ☆27Updated 4 months ago
- ☆14Updated 5 years ago
- HunyuanDiT with TensorRT and libtorch☆18Updated last year
- TensorRT简明教程☆26Updated 4 years ago
- 手摸手 美团 YOLOv6模型训练和TensorRT端到端部署方案教程☆34Updated 3 years ago
- paper-read-notes☆13Updated last year
- Wanwu models release, code will be released soon☆24Updated 3 years ago
- miemienet is a C++ AI deep learning inference framework.Supports PPYOLOE、PICODET.☆11Updated 2 years ago
- ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化☆50Updated 2 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
- ml模型分布式服务部署：grpc，flask；docker☆76Updated 4 years ago
- convert paddleOCR to torchOCR, ppocr-v3,ppocr-v4, onnx, openvino☆33Updated 2 years ago
- 基于rknn的yolov5的cpp实现，包含各种依赖库，是一个完整工程，可直接编译运行☆21Updated 3 years ago
- For 2022 Nvidia Hackathon☆22Updated 3 years ago
- 使用opencv部署DBNet文字检测，包含C++和Python两种版本的实现☆33Updated 4 years ago
- This repository is TensorRT implement of PINet☆18Updated 2 years ago
- ☆14Updated 3 years ago
- convert pytorch trained yolo model to ncnn for Flexible deployment☆10Updated 7 years ago
- ocr with yolo3 as feature extractor, implemented by keras, and accelerated by tensorrt☆34Updated 5 years ago