Skip to content

[gguf][torch.compile time] Convert to plain tensor earlier in dequantize_gguf_tensor #13166

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
DN6 merged 1 commit into from
Feb 20, 2026
+4 −1
Merged

[gguf][torch.compile time] Convert to plain tensor earlier in dequantize_gguf_tensor #13166

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
5 changes: 4 additions & 1 deletion src/diffusers/quantizers/gguf/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -516,6 +516,9 @@ def dequantize_gguf_tensor(tensor):

block_size, type_size = GGML_QUANT_SIZES[quant_type]

# Conver to plain tensor to avoid unnecessary __torch_function__ overhead.
tensor = tensor.as_tensor()
Comment on lines +519 to +520
Copy link
Member

@sayakpaul sayakpaul Feb 20, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does it have any impact on quality?


tensor = tensor.view(torch.uint8)
shape = _quant_shape_from_byte_shape(tensor.shape, type_size, block_size)

Expand All @@ -525,7 +528,7 @@ def dequantize_gguf_tensor(tensor):
dequant = dequant_fn(blocks, block_size, type_size)
dequant = dequant.reshape(shape)

return dequant.as_tensor()
return dequant


class GGUFParameter(torch.nn.Parameter):
Expand Down
Loading