ShaohonChen / Qwen3-SmVLLinks
将SmolVLM2的视觉头与Qwen3-0.6B模型进行了拼接微调
☆30Updated this week
Alternatives and similar repositories for Qwen3-SmVL
Users that are interested in Qwen3-SmVL are comparing it to the libraries listed below
Sorting:
- HunyuanDiT with TensorRT and libtorch☆17Updated last year
- ☆19Updated 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
- ffmpeg+cuvid+tensorrt+multicamera☆12Updated 6 months ago
- ☆22Updated last year
- 大模型部署实战:TensorRT-LLM, Triton Inference Server, vLLM☆26Updated last year
- An onnx-based quantitation tool.☆71Updated last year
- 天池 NVIDIA TensorRT Hackathon 2023 —— 生成式AI模型优化赛 初赛第三名方案☆49Updated last year
- Official implementation of the paper: “CountingDINO: A Training-free Pipeline for Exemplar-based Class-Agnostic Counting”☆36Updated last month
- Deploy RT-EDTR with onnx from paddlepaddle framwork and graph cut☆29Updated 2 years ago
- 用于学习GOT/Qwen/OnnxLLm☆52Updated 9 months ago
- YOLOv12 TensorRT 端到端模型加速推理和INT8量化实现☆13Updated 4 months ago
- ☆18Updated 2 years ago
- A tool convert TensorRT engine/plan to a fake onnx☆41Updated 2 years ago
- 这是一个使用opencv读取视频并使用socket进行传输视频画面的脚本文件,相较于调用ffmpeg传输节约了90%的数据量☆11Updated last year
- A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.☆222Updated 3 months ago
- Large Language Model Onnx Inference Framework☆36Updated 6 months ago
- ☆27Updated 3 weeks ago
- async inference for machine learning model☆26Updated 2 years ago
- Serving Inside Pytorch☆163Updated last week
- Train InternViT-6B in MMSegmentation and MMDetection with DeepSpeed☆95Updated 9 months ago
- README.md☆48Updated last year
- Python scripts performing Open Vocabulary Object Detection using the YOLO-World model in ONNX.☆56Updated last year
- ☆78Updated last year
- a simple lightweight large language model pipeline framework.☆26Updated 3 months ago
- ☆16Updated last year
- 高效部署:YOLO X, V3, V4, V5, V6, V7, V8, EdgeYOLO TRT推理 ™️ ,前后处理均由CUDA核函数实现 CPP/CUDA🚀☆49Updated 2 years ago
- Accelerate segment anything model inference using Tensorrt 8.6.1.6☆95Updated last year
- 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
- SAM and lama inpaint,包含QT的GUI交互界面,实现了交互式可实时显示结果的画点、画框进行SAM,然后通过进行Inpaint,具体操作看readme里的视频。☆48Updated last year