tsingmicro-toolchain / OnnxSlimLinks
A Toolkit to Help Optimize Large Onnx Model
☆157Updated last year
Alternatives and similar repositories for OnnxSlim
Users that are interested in OnnxSlim are comparing it to the libraries listed below
Sorting:
- A Toolkit to Help Optimize Onnx Model☆159Updated this week
- Large Language Model Onnx Inference Framework☆35Updated 5 months ago
- ☆99Updated 3 years ago
- Offline Quantization Tools for Deploy.☆129Updated last year
- Serving Inside Pytorch☆160Updated 2 weeks ago
- simplify >2GB large onnx model☆59Updated 6 months ago
- llm deploy project based onnx.☆42Updated 8 months ago
- stable diffusion using mnn☆68Updated last year
- A parser, editor and profiler tool for ONNX models.☆442Updated 2 weeks ago
- an example of segment-anything infer by ncnn☆121Updated 2 years ago
- MegEngine到其他框架的转换器☆70Updated 2 years ago
- A converter for llama2.c legacy models to ncnn models.☆81Updated last year
- ☆124Updated last year
- Count number of parameters / MACs / FLOPS for ONNX models.☆93Updated 7 months ago
- PyTorch Neural Network eXchange☆594Updated 2 weeks ago
- ☆71Updated 2 years ago
- mnn yolo demos.☆77Updated 8 months ago
- Common utilities for ONNX converters☆272Updated 6 months 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☆42Updated last year
- Compare multiple optimization methods on triton to imporve model service performance☆52Updated last year
- ☆120Updated 2 years ago
- ☆36Updated 8 months ago
- A simple tool that can generate TensorRT plugin code quickly.☆232Updated last year
- TensorRT encapsulation, learn, rewrite, practice.☆28Updated 2 years ago
- ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化☆48Updated last year
- Script to typecast ONNX model parameters from INT64 to INT32.☆107Updated last year
- Trans different platform's network to International Representation(IR)☆44Updated 7 years ago
- OneFlow->ONNX☆43Updated 2 years ago
- A pytorch to tensorrt convert with dynamic shape support☆260Updated last year
- ONNX2Pytorch☆162Updated 4 years ago