Lazily import torchao Int4WeightOnlyConfig to avoid side effects#40123
Open
n0kovo wants to merge 2 commits intohuggingface:mainfrom
Open
Lazily import torchao Int4WeightOnlyConfig to avoid side effects#40123n0kovo wants to merge 2 commits intohuggingface:mainfrom
n0kovo wants to merge 2 commits intohuggingface:mainfrom
Conversation
Previously, modeling_utils imported torchao.quantization.Int4WeightOnlyConfig at module load time if torchao was available. On CPU-only and Mac/Windows systems, this triggered a Triton ImportError print and a torch.distributed.elastic redirect warning, even if torchao quantization was not in use. This change replaces the eager import with a lazy import inside _load_shard_file(), preserving existing behavior while avoiding unnecessary side effects.
MekkCyber
approved these changes
Aug 25, 2025
Contributor
MekkCyber
left a comment
MekkCyber
left a comment
There was a problem hiding this comment.
Thanks for the fix 🤗 ! left a small comment
|
|
||
| if is_torchao_available(): | ||
| from torchao.quantization import Int4WeightOnlyConfig | ||
| Int4WeightOnlyConfig = None |
This was referenced Apr 29, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Previously,
modeling_utilsimportedtorchao.quantization.Int4WeightOnlyConfigat module load time iftorchaowas available.On CPU-only and Mac/Windows systems, this triggered a
torch.distributed.elasticredirect warning and a TritonImportErrorprint on certain versions (pytorch/ao#1842, pytorch/ao#1808):This change replaces the eager import with a lazy import inside _load_shard_file(), preserving existing behavior while avoiding unnecessary side effects.
cc @MekkCyber