[Qwen2_5_vl] - Onboarding Qwen2_5_vl model in QEfficient #560
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
mohiso22
force-pushed
the
qwen2vl
branch
2 times, most recently
from
c6f7151 to
e0c5d4e
Compare
Closed
quic-xiyushi
reviewed
Oct 8, 2025
mohiso22
requested review from
ochougul,
quic-amitraj,
quic-hemagnih and
quic-rishinr
as code owners
added 10 commits
October 14, 2025 19:24
Signed-off-by: Mohit Soni <[email protected]> Signed-off-by: Mohit Soni <[email protected]>
Signed-off-by: Mohit Soni <[email protected]>
Signed-off-by: Mohit Soni <[email protected]>
Signed-off-by: Mohit Soni <[email protected]>
Signed-off-by: Mohit Soni <[email protected]>
Signed-off-by: Mohit Soni <[email protected]>
Signed-off-by: Mohit Soni <[email protected]>
Signed-off-by: Mohit Soni <[email protected]>
Signed-off-by: Mohit Soni <[email protected]>
Signed-off-by: Mohit Soni <[email protected]>
Signed-off-by: Mohit Soni <[email protected]>
quic-rishinr
requested changes
Oct 15, 2025
|
|
||
| ## For AWQ model update pytorch version to 2.8.* | ||
| model_id = "Qwen/Qwen2.5-VL-32B-Instruct" | ||
| config = AutoConfig.from_pretrained(model_id) |
There was a problem hiding this comment.
Do we need to pass the config?
There was a problem hiding this comment.
No we can't in this transformer version
| return_tensors="pt", | ||
| ) | ||
|
|
||
| pos_ids, rope_deltas = qeff_model.model.get_rope_index( |
There was a problem hiding this comment.
can we do this part of the modelling file? Do we need to expose this to the user?
|
|
||
| inputs["position_ids"] = torch.arange(input_ids_length).view(1, 1, input_ids_length).expand(-1, batch_size, -1) | ||
|
|
||
| pos_ids, rope_deltas = qeff_model.model.model.get_rope_index( |
| patch_size = self.config.vision_config.patch_size | ||
| temporal_patch_size = self.config.vision_config.temporal_patch_size | ||
|
|
||
| IMAGE_FACTOR = 28 |
There was a problem hiding this comment.
Can we move this to constants file?
| @@ -0,0 +1,10 @@ | |||
| { | |||
There was a problem hiding this comment.
Why do we need this file?
|
can we add the tests for qwen 2.5 |
|
CI is passed |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
No description provided.