cubed
cubed copied to clipboard
cubed-dev
Bounded-memory serverless distributed N-dimensional array processing
Suggested by @dcherian in https://github.com/xarray-contrib/flox/pull/356#issuecomment-2083239661 to differentiate it from Dask.
Probably following this guide: https://learn.scientific-python.org/development/guides/packaging-classic/#git-tags-official-pypa-method
This issue tracks the work needed to support [Python array API standard v2023.12](https://data-apis.org/array-api/2023.12/index.html). The changes from the previous version are listed here: https://data-apis.org/array-api/2023.12/changelog.html#v2023-12 ## New array functions ### elemwise These...
We'd like to know the network throughput we are getting when doing object store IO. Lithops now exposes number of bytes sent and received (as mentioned here: https://github.com/cubed-dev/cubed/issues/234#issuecomment-1959778429) so that...
This is an umbrella issue for tracking the work on optimizations in Cubed. ## Creation optimizations Making creation operations more efficient, typically by not materializing unnecessary data. - [x] #336...
It would be useful to know how many backup tasks were run (for https://github.com/cubed-dev/cubed-benchmarks/issues/3), probably as a part of `TaskEndEvent` (number of backups run for the task, and possibly even...
From https://github.com/cubed-dev/cubed/actions/runs/8231307282/job/22506341591?pr=419: ``` FAILED array_api_tests/test_linalg.py::test_tensordot - AssertionError: out.shape=(1, 0), but should be (0, 0) [tensordot( (0, 0) . (0, 0) )] Falsifying example: test_tensordot( x1=cubed.Array, x2=cubed.Array, kw={'axes': ((-2,), (0,))}, )...