transformer-deploy
torch2trt
Our great sponsors
transformer-deploy | torch2trt | |
---|---|---|
8 | 5 | |
1,614 | 4,376 | |
0.7% | 1.4% | |
6.8 | 3.1 | |
6 months ago | 25 days ago | |
Python | Python | |
Apache License 2.0 | 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.
transformer-deploy
-
[D] How to get the fastest PyTorch inference and what is the "best" model serving framework?
For 2), I am aware of a few options. Triton inference server is an obvious one as is the ‘transformer-deploy’ version from LDS. My only reservation here is that they require the model compilation or are architecture specific. I am aware of others like Bento, Ray serving and TorchServe. Ideally I would have something that allows any (PyTorch model) to be used without the extra compilation effort (or at least optionally) and has some convenience things like ease of use, easy to deploy, easy to host multiple models and can perform some dynamic batching. Anyway, I am really interested to hear people's experience here as I know there are now quite a few options! Any help is appreciated! Disclaimer - I have no affiliation or are connected in any way with the libraries or companies listed here. These are just the ones I know of. Thanks in advance.
-
[P] Up to 12X faster GPU inference on Bert, T5 and other transformers with OpenAI Triton kernels
We work for Lefebvre Sarrut, a leading European legal publisher. Several of our products include transformer models in latency sensitive scenarios (search, content recommendation). So far, ONNX Runtime and TensorRT served us well, and we learned interesting patterns along the way that we shared with the community through an open-source library called transformer-deploy. However, recent changes in our environment made our needs evolve:
-
Convert Pegasus model to ONNX [Discussion]
here you will find a notebook for T5 on GPU with some tricks to make it fast: https://github.com/ELS-RD/transformer-deploy/blob/main/demo/generative-model/t5.ipynb
-
[P] What we learned by benchmarking TorchDynamo (PyTorch team), ONNX Runtime and TensorRT on transformers model (inference)
Check the notebook https://github.com/ELS-RD/transformer-deploy/blob/main/demo/TorchDynamo/benchmark.ipynb for detailed results, but what we will keep in mind:
-
[P] What we learned by making T5-large 2X faster than Pytorch (and any autoregressive transformer)
notebook: https://github.com/ELS-RD/transformer-deploy/blob/main/demo/generative-model/t5.ipynb (Onnx Runtime only)
-
[P] 4.5 times faster Hugging Face transformer inference by modifying some Python AST
Regarding CPU inference, quantization is very easy, and supported by Transformer-deploy , however performance on transformer are very low outside corner cases (like no batch, very short sequence and distilled model), and last Intel generation CPU based instance like C6 or M6 on AWS are quite expensive compared to a cheap GPU like Nvidia T4, to say it otherwise, on transformer, until you are ok with slow inference and takes a small instance (for a PoC for instance), CPU inference is probably not a good idea.
-
[P] First ever tuto to perform *GPU* quantization on 🤗 Hugging Face transformer models -> 2X faster inference
The end to end tutorial: https://github.com/ELS-RD/transformer-deploy/blob/main/demo/quantization_end_to_end.ipynb
-
[P] Python library to optimize Hugging Face transformer for inference: < 0.5 ms latency / 2850 infer/sec
Want to try it 👉 https://github.com/ELS-RD/transformer-deploy
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?
TensorRT - NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
TensorRT - PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
FasterTransformer - Transformer related optimization, including BERT, GPT
onnx-simplifier - Simplify your onnx model
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
OpenSeeFace - Robust realtime face and facial landmark tracking on CPU with Unity integration
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
mmrazor - OpenMMLab Model Compression Toolbox and Benchmark.
tensorrt_demos - TensorRT MODNet, YOLOv4, YOLOv3, SSD, MTCNN, and GoogLeNet
sparsednn - Fast sparse deep learning on CPUs
trt_pose - Real-time pose estimation accelerated with NVIDIA TensorRT