transformers
feat(quantizers): support non-weight param names in TorchAo safetensors loading
#46325
Open
Open
feat(quantizers): support non-weight param names in TorchAo safetensors loading #46325
agesf
wants to merge
3 commits into
huggingface:main
from
agesf:torchao-generic-weight-conversions
feat(quantizers): support non-weight param names in TorchAo safetenso…
ded84ab1
zucchini-nlp
commented
on 2026-06-01
Replace aten.normal_ patch with _is_hf_initialized; filter quantized …
24498181
zucchini-nlp
approved these changes
on 2026-06-04
Apply ruff formatting
e6b9084a
disabled auto-merge 14 hours ago
Manually disabled by user
Manually disabled by user
Login to write a write a comment.
Login via GitHub