DeepRecSys | http : //vlsiarch.eecs.harvard.edu/research/recommendation/

by harvard-acc Python Version: Current License: No License

X-Ray Key Features Code Snippets Community Discussions Vulnerabilities Install Support

kandi X-RAY | DeepRecSys Summary

DeepRecSys is a Python library. DeepRecSys has no bugs, it has no vulnerabilities and it has low support. However DeepRecSys build file is not available. You can download it from GitHub.

DeepRecSys provides an end-to-end infrastructure to study and optimize at-scale neural recommendation inference. The infrastructure is configurable across three main dimensions that represent different recommendation use cases: the load generator (query arrival patterns and size distributions), neural recommendation models, and underlying hardware platforms.

Support

Quality

Security

License

Reuse

Support

DeepRecSys has a low active ecosystem.

It has 51 star(s) with 10 fork(s). There are 9 watchers for this library.

It had no major release in the last 6 months.

There are 2 open issues and 4 have been closed. On average issues are closed in 73 days. There are no pull requests.

It has a neutral sentiment in the developer community.

The latest version of DeepRecSys is current.

Quality

DeepRecSys has 0 bugs and 0 code smells.

Security

DeepRecSys has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

DeepRecSys code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

DeepRecSys does not have a standard license declared.

Check the repository for any license declaration and review the terms closely.

Without a license, all rights are reserved, and you cannot use the library in your applications.

Reuse

DeepRecSys releases are not available. You will need to build from source code and install.

DeepRecSys has no build file. You will be need to create the build yourself to build the component from source.

Installation instructions, examples and code snippets are available.

DeepRecSys saves you 2085 person hours of effort in developing the same functionality from scratch.

It has 4575 lines of code, 183 functions and 27 files.

It has high code complexity. Code complexity directly impacts maintainability of the code.

Top functions reviewed by kandi - BETA

kandi has reviewed DeepRecSys and discovered the below as its top functions. This is intended to give you an instant insight into DeepRecSys implemented functionality, and help decide if they suit your requirements.

Construct an inference engine
Run queues
Create the model
Feed blob data
Run DeepRecSys
Command line interface
Initialize the model
Load the generator
Sleep generator function
Generate synthetic input data
Run an inference engine
Predict time for a given model
Predict time
Create sequential forward ops
Create a sequence of sequential forward ops
Create sequential forward operations
Parse the operations from a file
Create a sequence of parallel forward operations
Run the model
Calculate the distance from a trace
Wrap the given config file
Generate lru
Generate lru trace
Run MLP
Compute the graph
Run the graph
Generate a description

Get all kandi verified functions for this library.

DeepRecSys Key Features

No Key Features are available at this moment for DeepRecSys.

DeepRecSys Examples and Code Snippets

No Code Snippets are available at this moment for DeepRecSys.

Community Discussions

No Community Discussions are available at this moment for DeepRecSys.Refer to stack overflow page for discussions.

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install DeepRecSys

To get you started quickly, we have provided a number of examples scripts to run synthetic models, characterize hardware platforms, model at-scale inference, and optimizing scheduling decisions. The code is structured such that it enables maximum flexibility for future extensions. You can build the necessary python packages, using conda or docker environments, based on build/pip_requirements.txt.
The top-level is found in DeepRecSys.py. This co-ordinates the models, load generator, scheduler, and hardware backends.
Models can be found in the models directory.
The load generator is in loadGenerator.py
The scheduler is in scheduler.py
The CPU and accelerator inference engines are found in inferenceEngine.py and accelInferenceEngine.py respectively.