Skip to content

Subfunction changes qwen2 5#999

Merged
quic-rishinr merged 4 commits into
quic:mainfrom
abhishek-singh591:subfunction_changes_qwen2_5
May 22, 2026
Merged

Subfunction changes qwen2 5#999
quic-rishinr merged 4 commits into
quic:mainfrom
abhishek-singh591:subfunction_changes_qwen2_5

Conversation

@abhishek-singh591
Copy link
Copy Markdown
Contributor

@abhishek-singh591 abhishek-singh591 commented May 20, 2026

Performance Note

When compiling the Qwen2.5 vision encoder with subfunctions enabled, a performance degradation is observed. This is primarily due to a computation within the VisionAttention module that remains invariant across layers, resulting in unnecessary repeated execution and increased runtime overhead.

Signed-off-by: Abhishek Kumar Singh <sabhis@qti.qualcomm.com>
Signed-off-by: Abhishek Kumar Singh <sabhis@qti.qualcomm.com>
Signed-off-by: Abhishek Kumar Singh <sabhis@qti.qualcomm.com>
@quic-rishinr quic-rishinr self-requested a review May 21, 2026 08:36
Copy link
Copy Markdown
Contributor

@quic-rishinr quic-rishinr left a comment

Choose a reason for hiding this comment

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

LGTM Thanks!!

@quic-rishinr quic-rishinr merged commit 1128a68 into quic:main May 22, 2026
5 of 6 checks passed
quic-mohmeh pushed a commit to quic-mohmeh/efficient-transformers that referenced this pull request May 25, 2026
## Performance Note

When compiling the Qwen2.5 vision encoder with subfunctions enabled, a
performance degradation is observed. This is primarily due to a
computation within the VisionAttention module that remains invariant
across layers, resulting in unnecessary repeated execution and increased
runtime overhead.

---------

Signed-off-by: Abhishek Kumar Singh <sabhis@qti.qualcomm.com>
Signed-off-by: Mohit Mehta <mohmeh@qti.qualcomm.com>
smedhe pushed a commit to smedhe/QEff_Sharvari that referenced this pull request May 25, 2026
When compiling the Qwen2.5 vision encoder with subfunctions enabled, a
performance degradation is observed. This is primarily due to a
computation within the VisionAttention module that remains invariant
across layers, resulting in unnecessary repeated execution and increased
runtime overhead.

---------

Signed-off-by: Abhishek Kumar Singh <sabhis@qti.qualcomm.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants