Skip to content

Issues: jax-ml/ml_dtypes

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.

Sign up for GitHub

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

23 Open 27 Closed
23 Open 27 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

bfloat16 @ bfloat16 -> float32?
#235 opened Nov 13, 2024 by njzjz
@jakevdp
1
Free-threaded wheels on PyPI?
#228 opened Oct 30, 2024 by ngoldbaum
[RFC] Change float8_e5m2 dtype descr from <f1 to <V1
#216 opened Oct 1, 2024 by apivovarov
@hawkinsp
1
[Q] How to properly save and load fp8 NumPy arrays?
#207 opened Sep 25, 2024 by apivovarov
3
np.testing.assert_array_equal() not compatible with bfloat16 when the value is nan
#206 opened Sep 23, 2024 by ayaka14732
1
Type promotion behavior with Python scalars changed with NumPy 2
#189 opened Sep 13, 2024 by hawkinsp
Build of ml-dtypes 0.4.0 is failing on Power
#183 opened Sep 11, 2024 by sandeepgupta12
4
f16 sNaN is casted to f8e5m2 qNaN in Half_To_Float8E5m2 test
#162 opened Aug 1, 2024 by apivovarov
2
TBox
#150 opened May 18, 2024 by vxst
1
put a description ?
#149 opened Apr 28, 2024 by stonebig
1
Deserialization of float8_e5m2
#148 opened Apr 25, 2024 by wonjeon
@jakevdp
2
Support for non-saturating mode for fp8
#147 opened Apr 22, 2024 by wonjeon
Compilation Error in libtensorflow Pointing to float8.h in ml_dtype
#144 opened Apr 1, 2024 by HongMJ1315
6
bfloat16s (at least) throw error when given a format specifiier
#134 opened Jan 8, 2024 by colehaus
Custom floats do not respect np.set_printoptions bug Something isn't working
#125 opened Dec 5, 2023 by jakevdp
@hawkinsp
Make a 1.0 release and follow semantic versioning for breaking changes enhancement New feature or request
#111 opened Oct 6, 2023 by hawkinsp
Add complex32 and bcomplex32 enhancement New feature or request
#110 opened Oct 6, 2023 by hawkinsp
3
Deprecate creation of dtypes via np.dtype('typename')
#93 opened Sep 13, 2023 by jakevdp
4
data attribute raises a ValueError
#80 opened Jun 13, 2023 by joshlk
Add gtest instructions
#76 opened Jun 5, 2023 by awf
1
1
Feature Request: 8 bit fixed point numbers contributions welcome We welcome community contributions for this issue! enhancement New feature or request
#67 opened May 7, 2023 by jenkspt
2
Support np.testing.assert_array_max_ulp contributions welcome We welcome community contributions for this issue! enhancement New feature or request
#56 opened Apr 6, 2023 by mrahtz
1
bfloat16 & other custom dtypes incompatible with np.save bug Something isn't working
#41 opened Mar 23, 2023 by jakevdp
ProTip! Mix and match filters to narrow down what you’re looking for.