Skip to content

Fix torch.compile issue for LLM.int8() with threshold=0 #1581

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
matthewdouglas merged 1 commit into from
Apr 1, 2025
+8 −1
Merged

Fix torch.compile issue for LLM.int8() with threshold=0 #1581

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 bitsandbytes/autograd/_functions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,6 +84,13 @@ def get_inverse_transform_indices(
return permuted_tile_indices


# torch.compiler.is_compiling() is available only in torch >= 2.3
if hasattr(torch.compiler, "is_compiling"):
_is_compiling = torch.compiler.is_compiling
else:
_is_compiling = torch._dynamo.is_compiling


@deprecated(
"This function is deprecated and will be removed in a future release.",
category=FutureWarning,
Expand Down Expand Up @@ -174,7 +181,7 @@ def forward(
input_shape = A.shape

# Cast A to fp16
if A.dtype != torch.float16:
if A.dtype != torch.float16 and not _is_compiling():
warnings.warn(f"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization")

if len(A.shape) == 3:
Expand Down