Skip to content

Add OPAQUE packing format #2878

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 26, 2025
Merged

Add OPAQUE packing format #2878

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 8 additions & 1 deletion torchao/quantization/quantize_/common/packing_format.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,13 @@ class PackingFormat(str, Enum):
MARLIN_SPARSE = "marlin_sparse"

"""
Unpacked means the subbyte quantized data is stored as int8
Unpacked to int8 means the subbyte quantized data is stored as int8
"""
UNPACKED_TO_INT8 = "unpacked_to_int8"

"""
Opaque packing format that's used for tensors that does not have a predefined packing format
(that may be decided on hardware, tensor shape, library availability etc.) and it's not
needed for the rest of the system to understand the specific format that's adopted.
"""
OPAQUE = "opaque"
Loading