Project description

PyXIR

PyXIR is an Python Intermediate Representation (IR) for deep learning. It is designed to enable acceleration of deep neural networks from different frameworks, compiler stacks and IR's on hardware accelerators, specifically Xilinx FPGA based accelerators like DPU.

At the moment PyXIR integrates with the TVM Open Deep Learning compiler stack.

Project details

These details have not been verified by PyPI

GitHub Statistics

View statistics for this project via Libraries.io, or by using our public dataset on Google BigQuery

Release history Release notifications | RSS feed

This version

0.0.1

Mar 14, 2020

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pyxir-0.0.1.tar.gz (1.4 kB view hashes)

Uploaded Mar 14, 2020 Source

Built Distribution

pyxir-0.0.1-py3-none-any.whl (1.6 kB view hashes)

Uploaded Mar 14, 2020 Python 3

Hashes for pyxir-0.0.1.tar.gz

Hashes for pyxir-0.0.1.tar.gz
Algorithm	Hash digest
SHA256	`c15d885c5d980c3ef9fc0790159c209a28ef6789a4866504a8766ac880290c3a`
MD5	`2b3e6129805fc8fe3dad5322e95fc22c`
BLAKE2b-256	`b93bdd09ea5af4f542ec36b8f823faa14224bb5363377d85086b045b548e49c0`

Hashes for pyxir-0.0.1-py3-none-any.whl

Hashes for pyxir-0.0.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`49062ed0476625d2bd159588790dceb364b908e07d49895bbf56cf33e0e54cb5`
MD5	`2bfafa4413dae7dcb15941da9953d194`
BLAKE2b-256	`1bda1b7a4f4774074dcc6ccd13a96a78122d9ff39398fad21f6c0d3bb4b139e7`