deepsparse
onnxruntime
deepsparse | onnxruntime | |
---|---|---|
21 | 54 | |
2,878 | 12,736 | |
1.5% | 2.7% | |
9.5 | 10.0 | |
about 6 hours ago | 3 days ago | |
Python | C++ | |
GNU General Public License v3.0 or later | 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.
deepsparse
-
Fast Llama 2 on CPUs with Sparse Fine-Tuning and DeepSparse
Interesting company. Yannic Kilcher interviewed Nir Shavit last year and they went into some depth: https://www.youtube.com/watch?v=0PAiQ1jTN5k DeepSparse is on GitHub: https://github.com/neuralmagic/deepsparse
-
The future of quantization techniques in deep learning.
sparsity https://github.com/neuralmagic/deepsparse
-
[D] How to get the fastest PyTorch inference and what is the "best" model serving framework?
For 1), what is the easiest way to speed up inference (assume only PyTorch and primarily GPU but also some CPU)? I have been using ONNX and Torchscript but there is a bit of a learning curve and sometimes it can be tricky to get the model to actually work. Is there anything else worth trying? I am enthused by things like TorchDynamo (although I have not tested it extensively) due to its apparent ease of use. I also saw the post yesterday about Kernl using (OpenAI) Triton kernels to speed up transformer models which also looks interesting. Are things like SageMaker Neo or NeuralMagic worth trying? My only reservation with some of these is they still seem to be pretty model/architecture specific. I am a little reluctant to put much time into these unless I know others have had some success first.
-
[D] Most efficient open source language model ?
You should look into deepsparse, they are working on delivering GPU level performance on consumer CPUs with some great results: https://github.com/neuralmagic/deepsparse. There is a great interview with the founder, Nir Shavit here: https://piped.kavin.rocks/watch?v=0PAiQ1jTN5k
-
[R] New sparsity research (oBERT) enabled 175X increase in CPU performance for MLPerf submission
Utilizing the oBERT research we published at Neural Magic and some further iteration, we’ve enabled an increase in NLP performance of 175X while retaining 99% accuracy on the question-answering task in MLPerf. A combination of distillation, layer dropping, quantization, and unstructured pruning with oBERT enabled these large performance gains through the DeepSparse Engine. All of our contributions and research are open-sourced or free to use. Read through the oBERT paper on arxiv, try out the research in SparseML, and dive into the writeup to learn more about how we achieved these impressive results and utilize them for your own use cases!
-
An open-source library for optimizing deep learning inference. (1) You select the target optimization, (2) nebullvm searches for the best optimization techniques for your model-hardware configuration, and then (3) serves an optimized model that runs much faster in inference
Open-source projects leveraged by nebullvm include OpenVINO, TensorRT, Intel Neural Compressor, SparseML and DeepSparse, Apache TVM, ONNX Runtime, TFlite and XLA. A huge thank you to the open-source community for developing and maintaining these amazing projects.
-
[R] BERT-Large: Prune Once for DistilBERT Inference Performance
BERT-Large (345 million parameters) is now faster than the much smaller DistilBERT (66 million parameters) all while retaining the accuracy of the much larger BERT-Large model! We made this possible with Intel Labs by applying cutting-edge sparsification and quantization research from their Prune Once For All paper and utilizing it in the DeepSparse engine. It makes BERT-Large 12x smaller while delivering 8x latency speedup on commodity CPUs. We open-sourced the research in SparseML; run through the overview here and give it a try!
-
[R] How well do sparse ImageNet models transfer? Prune once and deploy anywhere for inference performance speedups! (arxiv link in comments)
And benchmark/deploy with 8X better performance in DeepSparse!
- Sparseserver.ui – test the performance of Sparse Transformers
-
[P] SparseServer.UI : A UI to test performance of Sparse Transformers
Hi _Arsenie, this runs the deepsparse.server command for multiple models. and btw, we recently updated the READMEs for the Deepsparse Engine https://github.com/neuralmagic/deepsparse
onnxruntime
-
Machine Learning with PHP
ONNX Runtime: ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
-
AI Inference now available in Supabase Edge Functions
Embedding generation uses the ONNX runtime under the hood. This is a cross-platform inferencing library that supports multiple execution providers from CPU to specialized GPUs.
-
Deep Learning in JavaScript
tfjs is dead, looking at the commit history. The standard now is to convert PyTorch to onnx, then use onnxruntime (https://github.com/microsoft/onnxruntime/tree/main/js/web) to run the model on the browsdr.
- FLaNK Stack 05 Feb 2024
-
Vcc – The Vulkan Clang Compiler
- slang[2] has the potential, but the meta programming part is not as strong as C++, existing libraries cannot be used.
The above conclusion is drawn from my work https://github.com/microsoft/onnxruntime/tree/dev/opencl, purely nightmare to work with thoes drivers and jit compilers. Hopefully Vcc can take compute shader more seriously.
[1]: https://www.circle-lang.org/
-
Oracle-samples/sd4j: Stable Diffusion pipeline in Java using ONNX Runtime
I did. It depends what you want, for an overview of how ONNX Runtime works then Microsoft have a bunch of things on https://onnxruntime.ai, but the Java content is a bit lacking on there as I've not had time to write much. Eventually I'll probably write something similar to the C# SD tutorial they have on there but for the Java API.
For writing ONNX models from Java we added an ONNX export system to Tribuo in 2022 which can be used by anything on the JVM to export ONNX models in an easier way than writing a protobuf directly. Tribuo doesn't have full coverage of the ONNX spec, but we're happy to accept PRs to expand it, otherwise it'll fill out as we need it.
- Mamba-Chat: A Chat LLM based on State Space Models
-
VectorDB: Vector Database Built by Kagi Search
What about models besides GPT? Most of the popular vector encoding models aren't using this architecture.
If you really didn't want PyTorch/Transformers, you could consider exporting your models to ONNX (https://github.com/microsoft/onnxruntime).
- ONNX runtime: Cross-platform accelerated machine learning
- Onnx Runtime: “Cross-Platform Accelerated Machine Learning”
What are some alternatives?
NudeNet - Neural Nets for Nudity Detection and Censoring
onnx - Open standard for machine learning interoperability
yolov5 - YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
onnx-tensorrt - ONNX-TensorRT: TensorRT backend for ONNX
openvino - OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
onnx-simplifier - Simplify your onnx model
model-optimization - A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
ONNX-YOLOv7-Object-Detection - Python scripts performing object detection using the YOLOv7 model in ONNX.
sparseml - Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
onnx-tensorflow - Tensorflow Backend for ONNX
tvm - Open deep learning compiler stack for cpu, gpu and specialized accelerators
MLflow - Open source platform for the machine learning lifecycle