Comments (3)
I will update the README. Thanks for your opinion.
from fastformers.
Thanks for your opinion.
We haven't tested the models on AMD CPUs. This is currently out of our scope of the project. It may or may not work correctly, but we don't actively maintain AMD environment.
from fastformers.
I understand that you haven't tested it on AMD but you simply shouldn't have to, unless you use a custom niche compiler, it should work just fine on any compliant x86-64 CPU.
I you still want to only mention Intel in the Readme out of paranoïa (sorry for the choice of word) it's fine but it will mislead users not to try your software because of a non existent risk.
Sidenotes:
Microsoft azure sell an increasing number of AMD epycs cpus.
The Xbox serie X of Microsoft is AMD based and use deep learning to some extent so they might use fastformers eventually.
from fastformers.
Related Issues (18)
- Task-agnostic or task-specific distillation used for CPU inference results? HOT 2
- Which TinyBERT models used for student initialisation? HOT 2
- pruned error HOT 3
- Add possibility to fine-tune on other tasks HOT 1
- SQuAD training issue HOT 1
- Fastformers/Transformers question HOT 4
- fastformer HOT 1
- integrate with Lightning ecosystem CI HOT 2
- how to convert int8 converted onnx model to tensorrt? HOT 1
- This repo is missing important files
- Support for XLnet HOT 2
- Run the teacher model (BERT-base) baseline Error HOT 2
- run the distilled student with 8-bit quantization (onnxruntime) HOT 6
- trying to train roberta-large model for question-answering task HOT 4
- Hyperparameters of SuperGLUE finetuning HOT 1
- Optimize fine-tuned model from HuggingFace HOT 3
- Integrate ZORB as an opt-in optimization HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fastformers.