oneflow VS serving

We are thrilled to announce the new release of OneFlow,, which is a deep learning framework designed to be user-friendly, scalable and efficient. OneFlow v0.9.0 contains 640 commits. For the full changelog, please check out: https://github.com/Oneflow-Inc/oneflow/releases/tag/v0.9.0.

Found relevant code at https://github.com/Oneflow-Inc/oneflow + all code implementations here

Check out OneFlow on GitHub . We'd love to hear your feedback!

OneFlow URL：https://github.com/Oneflow-Inc/oneflow/

No other options?:) We are developing a new distributed DL framework called OneFlow, which is faster than other frameworks and easier to use. Now it provides more and better PyTorch compatible APIs.

Code for https://arxiv.org/abs/2110.15032 found: https://github.com/Oneflow-Inc/oneflow

This article focuses on what is happening behind the execution of a Tensor in the deep learning framework OneFlow. It takes the operator oneflow.relu as an example to introduce the Interpreter and VM mechanisms that need to be relied on to execute this operator.

This article describes how OneFlow works with MLIR, how to add a graph-level Pass to OneFlow IR, how OneFlow Operations automatically become MLIR Operations, and why OneFlow IR can use MLIR to accelerate computations.

Backpressure mechanism, also known as credit-based flow control, is a classic scheme for network communication flow control problems. Its predecessor is the TCP sliding window. This idea is particularly simple and effective. As we will see in this article, based on the same principles, this idea is applicable to any flow control scheme and is found in the design of many hardware and software systems. In this article, the engineer of OneFlow will tell the chequered history of this simple idea.

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

[1] https://github.com/tensorflow/serving

I mean, probably - it's written in C++ https://github.com/tensorflow/serving

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

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.

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.

https://github.com/tensorflow/serving

https://thenewstack.io/tutorial-deploying-tensorflow-models-...

GitHub

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.