Skip to content
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

[Misc] Add assertion and helpful message for marlin24 compressed models #11388

Merged
merged 1 commit into from
Dec 23, 2024
Merged

[Misc] Add assertion and helpful message for marlin24 compressed models #11388

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
4 changes: 4 additions & 0 deletions ...el_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,10 @@ def create_weights(self, layer: torch.nn.Module, input_size: int,
params_dtype: torch.dtype, weight_loader: Callable,
**kwargs):

assert params_dtype == torch.float16, (
"float16 is required for marlin24 compressd models. Set dtype=torch.float16" # noqa: E501
)

pack_factor = 32 // self.quant_type.size_bits
output_size_per_partition = sum(output_partition_sizes)

Expand Down
Loading