Use float64 for SevenNet energy rescaling by default - #326
Merged
Conversation
The single-precision rescale path is a rarely-used backward-compat escape hatch, so threading a shift_scale_dtype argument through the calculator, checkpoint, deploy, mliap, torchsim, and CLI layers was excessive. Read the dtype from the SEVENN_SHIFT_SCALE_DTYPE env var at the single point where the shift/scale parameters are created (sevenn/nn/scale.py), matching the existing SEVENN_DEBUG-style toggles. Reverts the argument plumbing in _const, _keys, checkpoint, mliap, model_build, sevenn_get_model, and util (now identical to base). Keeps the behavioral changes: double-precision rescale forward casts, C++ energy in double, torchsim output casts, D3 output float32 cast, and loss dtype alignment. deploy still records the resolved dtype in metadata via resolve_shift_scale_dtype(). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Member
|
LGTM🔥 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I left the single precision option for backward compatibility.