serving
MNN
Our great sponsors
serving | MNN | |
---|---|---|
12 | 3 | |
6,070 | 8,278 | |
0.3% | 1.1% | |
9.8 | 8.1 | |
about 7 hours ago | 11 days ago | |
C++ | C++ | |
Apache License 2.0 | - |
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.
serving
-
Llama.cpp: Full CUDA GPU Acceleration
Yet another TEDIOUS BATTLE: Python vs. C++/C stack.
This project gained popularity due to the HIGH DEMAND for running large models with 1B+ parameters, like `llama`. Python dominates the interface and training ecosystem, but prior to llama.cpp, non-ML professionals showed little interest in a fast C++ interface library. While existing solutions like tensorflow-serving [1] in C++ were sufficiently fast with GPU support, llama.cpp took the initiative to optimize for CPU and trim unnecessary code, essentially code-golfing and sacrificing some algorithm correctness for improved performance, which isn't favored by "ML research".
NOTE: In my opinion, a true pioneer was DarkNet, which implemented the YOLO model series and significantly outperformed others [2]. Same trick basically like llama.cpp
-
[D] How do OpenAI and other companies manage to have real-time inference on model with billions of parameters over an API?
I mean, probably - it's written in C++ https://github.com/tensorflow/serving
-
Should I wait for the M2 Macbook Pro?
We’re looking into that solution at the moment, the issue I’m referring to is related to this https://github.com/tensorflow/serving/issues/1948 we’ll know if the plug-in approach works for our uses soon but haven’t started looking into implementing it yet
- TF Serving has been unavailable for 9 days so far due to outdated GPG key
- TF Serving has been unavailable for 8 days
-
Would you use maturin for ML model serving?
Which ML framework do you use? Tensorflow has https://github.com/tensorflow/serving. You could also use the Rust bindings to load a saved model and expose it using one of the Rust HTTP servers. It doesn't matter whether you trained your model in Python as long as you export its saved model.
-
Is LaMDA Sentient? – An Interview [pdf]
Most likely it's a model server running something like https://github.com/tensorflow/serving and if there isn't a lot of load, the resource could kill some of its tasks. I wouldn't imagine it's sitting around pondering deep thoughts.
- Ask HN: How to deploy a TensorFlow model for access through an HTTP endpoint?
-
Popular Machine Learning Deployment Tools
GitHub
-
If data science uses a lot of computational power, then why is python the most used programming language?
You serve models via https://www.tensorflow.org/tfx/guide/serving which is written entirely in C++ (https://github.com/tensorflow/serving/tree/master/tensorflow_serving/model_servers), no Python on the serving path or in the shipped product.
MNN
-
[D][R] Deploying deep models on memory constrained devices
However, I am looking on this subject through the problem of training/finetuning deep models on the edge devices, being increasingly available thing to do. Looking at tflite, alibaba's MNN, mit-han-lab's tinyengine etc..
-
What’s New in TensorFlow 2.10?
There are a ton of mobile deployment options that support PyTorch+TF models. It's hard to argue TFLite is the best.
-
Newbie having error code of cannot build selected target abi x86 no suitable splits configured
I found a solution on GitHub check your app's build.gradle, defaultConfig section - you need to add x86 to your ndk abiFilters ndk.abiFilters 'armeabi-v7a','arm64-v8a', 'x86' GitHub Hope it will help. You have to find that file and edit it as given here
What are some alternatives?
server - The Triton Inference Server provides an optimized cloud and edge inferencing solution.
tensorflow - An Open Source Machine Learning Framework for Everyone
flashlight - A C++ standalone library for machine learning
TNN - TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.
XLA.jl - Julia on TPUs
ncnn - ncnn is a high-performance neural network inference framework optimized for the mobile platform
glow - Compiler for Neural Network hardware accelerators
ML-examples - Arm Machine Learning tutorials and examples
oneflow - OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
julia - The Julia Programming Language
OpenMLDB - OpenMLDB is an open-source machine learning database that provides a feature platform computing consistent features for training and inference.