Describe the bug

max_shard_size=1GB is set but the size of each safetensor is still greater than 1GB

Reproduction

pipe.save_pretrained(save_directory='FLUX.1-dev-Control-all', max_shard_size="1GB")

Logs

System Info

diffusers=0.30.2
accelerate=1.7.0
transformers=4.52.4

Who can help?

No response