sparsednn
TensorRT
Our great sponsors
sparsednn | TensorRT | |
---|---|---|
1 | 5 | |
51 | 2,340 | |
- | 3.7% | |
0.0 | 9.5 | |
over 1 year ago | 1 day ago | |
Python | Python | |
Apache License 2.0 | BSD 3-clause "New" or "Revised" 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.
sparsednn
-
[P] 4.5 times faster Hugging Face transformer inference by modifying some Python AST
If you are ever interested in looking at pruning, happy to integrate my open source library https://github.com/marsupialtail/sparsednn. Latest update has unstructured and structured sparse int8 kernels. 3x speedup over dense int8 at 90 percent sparsity with 1x4 blocks.
TensorRT
- Learn TensorRT optimization
- I made TensorRT example. I hope this will help beginners. And I also have a question about TensorRT best practice.
- [P] [D] I made TensorRT example. I hope this will help beginners. And I also have a question about TensorRT best practice.
-
[P] 4.5 times faster Hugging Face transformer inference by modifying some Python AST
Have you tried the new Torch-TensorRT compiler from NVIDIA?
-
PyTorch 1.10
You can quantize your model to FP16 or Int8 using PTQ as well and it should give you an additional speed up inference wise.
Here is a tutorial[2] to leverage TRTorch.
[1] https://github.com/NVIDIA/TRTorch/tree/master/core
What are some alternatives?
transformer-deploy - Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀
torch2trt - An easy to use PyTorch to TensorRT converter
mmrazor - OpenMMLab Model Compression Toolbox and Benchmark.
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
cutlass - CUDA Templates for Linear Algebra Subroutines
onnx-simplifier - Simplify your onnx model
TensorRT - NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
jetson - Self-driving AI toy car 🤖🚗.
vision - Datasets, Transforms and Models specific to Computer Vision
mlops-course - Learn how to design, develop, deploy and iterate on production-grade ML applications.
nn - 🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠