No project description provided
Project description
ml_dtypes
This is not an officially supported Google product.
ml_dtypes
is a stand-alone implementation of several NumPy dtype extensions used in machine learning libraries, including:
bfloat16
: an alternative to the standardfloat16
formatfloat8_*
: several experimental 8-bit floating point representations including:float8_e4m3b11
float8_e4m3fn
float8_e5m2
Installation
We will soon release pre-built wheels for this package at http://pypi.org/project/ml-dtypes, so this package can be easily pip installed.
To build locally, clone the repository and run:
$ git submodule init
$ git submodule update
$ pip install .
Example Usage
>>> from ml_dtypes import bfloat16
>>> import numpy as np
>>> np.zeros(4, dtype=bfloat16)
array([0, 0, 0, 0], dtype=bfloat16)
Importing ml_dtypes
also registers the data types with numpy, so that they may
be referred to by their string name:
>>> np.dtype('bfloat16')
dtype(bfloat16)
>>> np.dtype('float8_e5m2')
dtype(float8_e5m2)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ml_dtypes-0.0.2rc4.tar.gz
(682.9 kB
view hashes)
Built Distributions
Close
Hashes for ml_dtypes-0.0.2rc4-cp311-cp311-win_amd64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 01529520c5382abb9abfcb5ea0fb57529f9b43bd2b7fc279078de60f5c26f3cf |
|
MD5 | 6d9fc957d17cac61bff655e1853cd33a |
|
BLAKE2b-256 | 5337735ea2edf931790c86bfd7d00e7e3d7e5c17727cacef69c093659e9a9aaf |
Close
Hashes for ml_dtypes-0.0.2rc4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 212009a3f90e729a6a2852986549482425c3d5e271d9f5892ed5cbe8271bc9df |
|
MD5 | 2363b9bb56d27c28ef645186caf25394 |
|
BLAKE2b-256 | 625f16ce60b790a3c63215d50222a8b8ebf3772f8e3631076320661f422824d8 |
Close
Hashes for ml_dtypes-0.0.2rc4-cp311-cp311-macosx_10_9_universal2.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b4d1d9863cea3794e7b6c46a9c67c12fef4f357398921e581722b8994f62290b |
|
MD5 | 2f88771e67bdf6f99fb14a0df6be4ce2 |
|
BLAKE2b-256 | 081cf712baee9c938a4f95ac8ab4f3cbc9aa3c3a4fb00a1d49531764b1d34368 |
Close
Hashes for ml_dtypes-0.0.2rc4-cp310-cp310-win_amd64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9246a5e42dfaa64d015d21d48101f503e63b335ba3f6f51973a3ef9d6bf9361a |
|
MD5 | 908ba9aba58745ae1c239131a261149a |
|
BLAKE2b-256 | 23d117dc1bb41836f6e4743e18cd7a4c2ce35ad50edaa8f7fd901bd685669d47 |
Close
Hashes for ml_dtypes-0.0.2rc4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 517c4496007a200766f625f9a693f67c0e3ad28b79d54ab67f4b6ec5b6b3278c |
|
MD5 | ea6734ced0cb178f8cdf46efc361fcd4 |
|
BLAKE2b-256 | 4cb9687ec6525a0616175255a4a43f24c38431aaf0ba3f7c579298dd07ba33dd |
Close
Hashes for ml_dtypes-0.0.2rc4-cp310-cp310-macosx_10_9_universal2.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d12e05ff0ce313d4141ed49124a09d7a216d21957751adbf08f1054adce13d0a |
|
MD5 | 2d58f4f49115a59b40b94f7da68cc14f |
|
BLAKE2b-256 | 910ee2fa1b233205ca51b69154fc95ff381a09872c3653036cf30e607f1f0d2e |
Close
Hashes for ml_dtypes-0.0.2rc4-cp39-cp39-win_amd64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | a7b10caf83c652be1bb6d24f1a87ba69a433d23a98115df9a528d9a117257d7a |
|
MD5 | 81af23c8bbd180074c8d99c4ff45177b |
|
BLAKE2b-256 | 449389343aca4e62a4d4c03256d9e167a719e3bfe15f501e88346b95c17b78f9 |
Close
Hashes for ml_dtypes-0.0.2rc4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | c4ef24f64d62a63253a71b9ba848b4a4f15d5147a94db854d7e831fe570d2e64 |
|
MD5 | 4f741f3805d8bc123faa694a1d370722 |
|
BLAKE2b-256 | 7a2df075e12882dd460126ec0318a77f70b1ddcca110b4887a74778b22b0c03c |
Close
Hashes for ml_dtypes-0.0.2rc4-cp39-cp39-macosx_10_9_universal2.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | f99616f3304aaaf02ebe9b6912e4adf16b0e3364f35cb9df592617331744f773 |
|
MD5 | 7a71ebf8bbdc5150639cbb37740b1da1 |
|
BLAKE2b-256 | 861f414656b9a29b094e4cbd1545b8a773e6eee99374188bb3570564d5c2ef05 |
Close
Hashes for ml_dtypes-0.0.2rc4-cp38-cp38-win_amd64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 59666a3f94d6831210e8e8ca97fa8948ba099854f3548ffabe52304eddc4c423 |
|
MD5 | adebfb2008a9feab36bd0ce3353673e9 |
|
BLAKE2b-256 | 574224710448676c0f6861d26bb7dfef273a99e2fc0fe937ea1def0218bb6653 |
Close
Hashes for ml_dtypes-0.0.2rc4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 299763c225f14e3f0ea9a01d5b40df556406d8be993aa4ea72aa4423347dc6f1 |
|
MD5 | ace8ced3bfbdb1cdc8f2b46f54e8be9f |
|
BLAKE2b-256 | a5f693946b8198bdc8b04b40f4a13f954f2757e4786f7b29b70960e41edba2c6 |
Close
Hashes for ml_dtypes-0.0.2rc4-cp38-cp38-macosx_10_9_universal2.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | c2080ad4822d1c139a3bd8385e71f7930c7207b2b56bc69cbc2307efff80045b |
|
MD5 | 7f6f2a66620673a5221e90a01e12ff50 |
|
BLAKE2b-256 | 6cf291296d0113d393be9496ef025cb1fd283bd2b907abf24619361d36958e59 |