An awesome tool/library benchmark LLM performance on all kinds of hardware!
Project description
Impetus
An awesome tool/library benchmark LLM performance on all kinds of hardware!
Explore the docs »
View Demo
·
Report Bug
·
Request Feature
Table of Contents
About The Project
Getting Started
Installation
Installation with pip is simple as follows:
pip install impetus
Usage
For more examples, please refer to the Documentation
Developing locally
This project use poetry for dependency management, and is required for running impetus locally.
- Clone the repo
git clone https://github.com/dhmnr/impetus.git
- Install Dependencies
poetry install - Run the command as follows
poetry shell run impetus --help
Roadmap
- Support Quantization
- Multiple GPU support with accelerate
- GPU/CPU usage information
- Flops/MFU information
- Detailed breakdown, | self-attention | FFN | lm_head
- Support BERT and VLMs and others
- Support different backends
Minor Fixes
- Support different datasets
See the open issues for a full list of proposed features (and known issues).
Contributing
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Top contributors:
License
Distributed under the MIT License. See LICENSE.txt for more information.
Contact
Project Link: https://github.com/dhmnr/impetus
Acknowledgments
Use this space to list resources you find helpful and would like to give credit to. I've included a few of my favorites to kick things off!
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
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file impetus-0.1.1.tar.gz.
File metadata
- Download URL: impetus-0.1.1.tar.gz
- Upload date:
- Size: 10.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.8.3 CPython/3.10.12 Linux/5.15.0-100-generic
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4d5dddf13223ec3c2088f10b7084f0150b0f98130f8e977ba02ddce4ab8e14ea
|
|
| MD5 |
1094feb47d0865de52357e3e765a4d02
|
|
| BLAKE2b-256 |
010e7b226172f298327545b2a32ea07beaad4a2ecaa1fe0c973ac038e8a3c879
|
File details
Details for the file impetus-0.1.1-py3-none-any.whl.
File metadata
- Download URL: impetus-0.1.1-py3-none-any.whl
- Upload date:
- Size: 10.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.8.3 CPython/3.10.12 Linux/5.15.0-100-generic
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
955379b3fa99adf0cff2c58f290c5ea8684b4eb3c71476ab1d9040e83409108d
|
|
| MD5 |
f730d78325bbbb82bd15da29e721a15c
|
|
| BLAKE2b-256 |
e4f25a369551fe2d91261b9c7d051fd601ce87f3e1fda2b3514eecc89bb46719
|