OnnxSlim: A Toolkit to Help Optimize 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 ❤️❤️❤️
- 🚀 OnnxSlim is merged into transformers.js 🤗🤗🤗
Installation
Using Prebuilt
pip install onnxslim
Install From Source
pip install git+https://github.com/inisis/OnnxSlim@main
Install From Local
git clone https://github.com/inisis/OnnxSlim && cd OnnxSlim/
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-0.1.39.tar.gz
(119.7 kB
view details)
Built Distribution
onnxslim-0.1.39-py3-none-any.whl
(141.8 kB
view details)
File details
Details for the file onnxslim-0.1.39.tar.gz
.
File metadata
- Download URL: onnxslim-0.1.39.tar.gz
- Upload date:
- Size: 119.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.9.20
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 46b647138d62da124aa679935cbce5bde10cf1de494772b56231966fc904c1b8 |
|
MD5 | b67e3f3724a3edebda3c00212af41e1a |
|
BLAKE2b-256 | 286ef74a93b1e077357e42202d1ad8635174f2a7d4c16a0edd590a90f98de09f |
File details
Details for the file onnxslim-0.1.39-py3-none-any.whl
.
File metadata
- Download URL: onnxslim-0.1.39-py3-none-any.whl
- Upload date:
- Size: 141.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.9.20
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3d4a47563b36201ce5e886e19cc99c872f8d1e04eeb76b952616f5946b82aa53 |
|
MD5 | 4ff6509c7340ed5b4d6ea36384949fdb |
|
BLAKE2b-256 | 0c893b9acb813e7c520a5aa8c2edba48bb4bc07410e7110a7357c93970ca7001 |