Fix compile error for Gemma3 multimodal inputs #671
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jiminha
requested review from
adobrzyn,
afierka-intel,
iboiko-habana,
kamil-kaczor,
ksmusz,
kzawora-intel,
mgawarkiewicz-intel,
michalkuligowski,
vivekgoe and
xuechendi
as code owners
🚧 CI BlockedThe main CI workflow was not started for the following reason:
|
yafshar
reviewed
Dec 2, 2025
| class HPUConv2dLayer(Conv2dLayer): | ||
|
|
||
| def _forward_mulmat(self, x: torch.Tensor) -> torch.Tensor: | ||
| assert x.dim() == 4 |
Contributor
There was a problem hiding this comment.
Suggested change
| assert x.dim() == 4 | |
| assert x.dim() == 4, f"Expected NCHW, got {x.shape}" |
slightly clearer version
yafshar
reviewed
Dec 2, 2025
yafshar
reviewed
Dec 2, 2025
✅ CI PassedAll checks passed successfully against the following vllm commit: |
-replace unfold to view/reshape -replace text embedding to avoid dynamic shape -remove merge_multimodal replacement since masked_scatter issue is fixed -enable gemma3 model test Signed-off-by: Jimin Ha <jimin.ha@intel.com>
jiminha
force-pushed
the
jha/gemma3_textembedding
branch
from
29431db to
bc58c71
Compare
🚧 CI BlockedThe main CI workflow was not started for the following reason:
|
Signed-off-by: Jimin Ha <jimin.ha@intel.com>
🚧 CI BlockedThe main CI workflow was not started for the following reason:
|
✅ CI PassedAll checks passed successfully against the following vllm commit: |
iboiko-habana
approved these changes
Dec 3, 2025
mhelf-intel
pushed a commit
to mhelf-intel/vllm-gaudi
that referenced
this pull request
Dec 5, 2025
Due to the latest changes from upstream, gemma3 is failing to compile on HPU vllm-project/vllm#27772 vllm-project/vllm#28842 -replace unfold to view/reshape -replace text embedding to avoid dynamic shape -remove merge_multimodal replacement since masked_scatter issue is fixed -enable back gemma3 model test --------- Signed-off-by: Jimin Ha <jimin.ha@intel.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Due to the latest changes from upstream, gemma3 is failing to compile on HPU
vllm-project/vllm#27772
vllm-project/vllm#28842
-replace unfold to view/reshape
-replace text embedding to avoid dynamic shape
-remove merge_multimodal replacement since masked_scatter issue is fixed
-enable back gemma3 model test