sparktorch
torch2trt
sparktorch | torch2trt | |
---|---|---|
1 | 5 | |
334 | 4,395 | |
- | 1.0% | |
2.5 | 3.1 | |
12 months ago | 6 days ago | |
Python | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
sparktorch
-
Spark2 + pytorch on GPU
Was reading the documentation of sparktorch (https://github.com/dmmiller612/sparktorch) which says you need spark >= 2.4.4. But to the best of my knowledge spark2 doesn't have gpu compute capabilities. Does that mean it can only use cpu compute? Am I missing something?
torch2trt
- [D] How you deploy your ML model?
-
PyTorch 1.10
Main thing you want for server inference is auto batching. It's a feature that's included in onnxruntime, torchserve, nvidia triton inference server and ray serve.
If you have a lot of preprocessing and post logic in your model it can be hard to export it for onnxruntime or triton so I usually recommend starting with Ray Serve (https://docs.ray.io/en/latest/serve/index.html) and using an actor that runs inference with a quantized model or optimized with tensorrt (https://github.com/NVIDIA-AI-IOT/torch2trt)
-
Jetson Nano: TensorFlow model. Possibly I should use PyTorch instead?
https://github.com/NVIDIA-AI-IOT/torch2trt <- pretty straightforward https://github.com/jkjung-avt/tensorrt_demos <- this helped me a lot
-
How to get TensorFlow model to run on Jetson Nano?
I find Pytorch easier to work with generally. Nvidia has a Pytorch --> TensorRT converter which yields some significant speedups and has a simple Python API. Convert the Pytorch model on the Nano.
What are some alternatives?
pytorch-lightning - Build high-performance AI models with PyTorch Lightning (organized PyTorch). Deploy models with Lightning Apps (organized Python to build end-to-end ML systems). [Moved to: https://github.com/Lightning-AI/lightning]
TensorRT - PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
fastT5 - ⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
onnx-simplifier - Simplify your onnx model
BERT-NER - Pytorch-Named-Entity-Recognition-with-BERT
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
openfl - An open framework for Federated Learning.
transformer-deploy - Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀
polyaxon - MLOps Tools For Managing & Orchestrating The Machine Learning LifeCycle
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
pytorch-lightning - Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.
tensorrt_demos - TensorRT MODNet, YOLOv4, YOLOv3, SSD, MTCNN, and GoogLeNet