diffusers
bb35ec9f - fix(bnb): defer 8-bit weights split from their SCB stats across shards

Commit
11 days ago
fix(bnb): defer 8-bit weights split from their SCB stats across shards Sharded serialization can place an 8-bit weight and its `SCB` statistics in different shard files, in which case the shard-by-shard loader failed with "Missing quantization component `SCB`". Hold the incomplete half of the pair back until its counterpart arrives with a later shard, mirroring the torchao pending mechanism, and disable parallel shard loading for prequantized 8-bit checkpoints. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Author
sayak@huggingface.co
Committer
sayak@huggingface.co
Parents
Loading