Closed raimis closed 1 year ago
Sounds good to me.
I would like to test this https://github.com/openmm/NNPOps/pull/80 a bit more. For this https://github.com/openmm/NNPOps/issues/84 I say we jump straight to torch 2.0, probably solving 1.13 in the process. Lets make 0.4 now.
yep go ahead!
A release is created: https://github.com/openmm/NNPOps/releases/tag/v0.4
Now, let's see if conda-forge
is going to pick it up automatically.
The package builds fail because of a tolerance issue with the new tests.
yeah it is failing the tolerance test (which pass on the github actions CI which run on this repo) grad_error = 0.0074 fails in the assert(grad_error < 7e-3)
. I can reduced the tolerance to assert(grad_error < 8e-3)
or even 1e-2
. These seem like reasonably loose tolerances to me, are these what we expect from float32
precision gradient calculations? @raimis @peastman
I'm working on that.
Packages are available: https://anaconda.org/conda-forge/nnpops/files?version=0.4
@jchodera could you tweet about the release (https://github.com/openmm/NNPOps/releases/tag/v0.4)
Done!
It is time for the next release with:
81
83
Especially the PBC fix (#83). Does anybody working on something and wants to include it?
Ping: @peastman @RaulPPelaez @sef43