Skip to content

[ET-VK][qlinear] Look through output view_copy when detecting output quantization #18014

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
meta-codesync merged 4 commits into from
Mar 10, 2026
Merged

[ET-VK][qlinear] Look through output view_copy when detecting output quantization #18014

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3adaa89
[ET-VK][qlinear] Look through output view_copy when detecting output …
Mar 9, 2026
2a79ce7
Update on "[ET-VK][qlinear] Look through output view_copy when detect…
Mar 9, 2026
88e1310
Update on "[ET-VK][qlinear] Look through output view_copy when detect…
Mar 9, 2026
d7eda9c
Update on "[ET-VK][qlinear] Look through output view_copy when detect…
Mar 9, 2026
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: 9 additions & 0 deletions backends/vulkan/patterns/quantized_linear.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -174,12 +174,21 @@ def __init__(self, mm_node: torch.fx.Node) -> None: # noqa: C901

# Check if the output is also quantized (q → dq → linear → q pattern)
# Also handle fused linear+relu (q → dq → linear → relu → q pattern)
# Due to decomposition of aten.linear for 3D+ inputs, there may be a
# view_copy between the mm output and the quantize node.
self.quantize_output_node = None
self.output_scales_node = None
self.output_zeros_node = None
self.relu_node = None
self.output_view_copy_node = None
if len(self.output_node.users) == 1:
cur_node = list(self.output_node.users)[0]
# Skip potential view_copy between linear and output quantize
if utils.is_view_copy_node(cur_node) and len(cur_node.users) == 1:
self.output_view_copy_node = cur_node
self.all_nodes.append(self.output_view_copy_node)
self.output_node = self.output_view_copy_node
cur_node = list(cur_node.users)[0]
if cur_node.target == exir_ops.edge.aten.relu.default:
self.relu_node = cur_node
if len(cur_node.users) == 1:
Expand Down
Loading