fix bug for videomt model device mismatch#45204
Conversation
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>
| ) | ||
| query_tokens = self.query_updater(propagated_query).to(frame_hidden_states.device) + self.query.weight[ | ||
| None, :, : | ||
| ].to(frame_hidden_states.device) |
There was a problem hiding this comment.
since we have this change now, we don't need the
query_tokens.to(frame_hidden_states.device)
below.
It's no big deal, but let's remove it.
There was a problem hiding this comment.
Thx for the advice. Done.
|
Could you share which tests are failing without this PR, as well as the (full) error log you have for them, please 🙏 ? Thanks |
|
Sure. Before this PR, when I use 4 cards to run test case like: |
|
Thank you for the provided information. Indeed, this model's integration tests have
which will lead this kind of issues. So the fix makes a lot of sense (even for user-facing, not just for CI). |
|
run-slow: videomt |
|
This comment contains models: ["models/videomt"] |
|
run-slow: videomt |
|
[For maintainers] Suggested jobs to run (before merge) run-slow: videomt |
|
This comment contains models: ["models/videomt"] |
* fix bug for videomt model device mismatch Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com> * update Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com> * fix --------- Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com> Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
@ydshieh pls help review, thx!