OnnxSlim: A Toolkit to Help Optimize Large Onnx Model
Project description
OnnxSlim
OnnxSlim can help you slim your onnx model, with less operators, but same accuracy, better inference speed.
- 🚀 OnnxSlim is merged to mnn-llm, performance increased by 5%
- 🚀 Rank 1st in the AICAS 2024 LLM inference optimization challenge held by Arm and T-head
- 🚀 OnnxSlim is merged into ultralytics ❤️❤️❤️
Installation
Using Prebuilt
pip install onnxslim
Build From Source
pip install .
How to use
onnxslim your_onnx_model slimmed_onnx_model
For more usage, see onnxslim -h or refer to our examples
References
Contact
Discord: https://discord.gg/nRw2Fd3VUS QQ Group: 873569894
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
onnxslim-0.1.30.tar.gz
(114.3 kB
view hashes)
Built Distribution
onnxslim-0.1.30-py3-none-any.whl
(128.3 kB
view hashes)
Close
Hashes for onnxslim-0.1.30-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | ab761ccbcfd93dbf34b7d42f5983cd9da4be73e5b786fd4c2f927050ddbe97ce |
|
MD5 | 25a4bb96deec55765f7a1b2621118abb |
|
BLAKE2b-256 | 41b1db351f21fba49856b0c1dca4b44e8c71b9c3746b04cba60e8d8c05129391 |