Skip to content

Add workaround to recover the perf for quantized vit in torch.compile #926

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
Sep 24, 2024
Merged

Add workaround to recover the perf for quantized vit in torch.compile #926

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
3 changes: 3 additions & 0 deletions tutorials/quantize_vit/run_vit_b_quant.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,9 @@
if not TORCH_VERSION_AT_LEAST_2_5:
unwrap_tensor_subclass(model)

# temporary workaround to recover the perf with quantized model under torch.compile
torch.backends.mha.set_fastpath_enabled(False)

model = torch.compile(model, mode='max-autotune')

# Must run with no_grad when optimizing for inference
Expand Down
Loading