-
Notifications
You must be signed in to change notification settings - Fork 3.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add normal distribution to random engines #1352
Conversation
python/tvm/contrib/random.py
Outdated
@@ -55,4 +55,29 @@ def uniform(low, high, size): | |||
return _api.extern(size, [], lambda ins, outs: _intrin.call_packed( | |||
"tvm.contrib.random.uniform", float(low), float(high), outs[0]), dtype='float32') | |||
|
|||
|
|||
def normal(mean, stddev, size): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
make API arguments consistent when there is numpy API available,
https://docs.scipy.org/doc/numpy/reference/generated/numpy.random.normal.html
@nhynes can you act on the comment? |
@nhynes please also update the naming convention of python API and docstring |
fixed. sorry for the oversight |
This PR adds functionality for sampling from an isotropic Gaussian distribution to `contrib.random. This PR implements the ziggurat algorithm.