Continuous Batching for VLMs #610
Open
+929
−179
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
asmigosw
requested review from
ochougul,
quic-amitraj,
quic-hemagnih and
quic-rishinr
as code owners
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
asmigosw
force-pushed
the
CB_VLM_update
branch
from
b89ea66 to
9a42a08
Compare
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
quic-mamta
reviewed
Nov 28, 2025
| Args: | ||
| vision_session: QAICInferenceSession for vision model | ||
| processor: AutoImageProcessor for image preprocessing | ||
| tokenizer: AutoTokenizer for text tokenization |
Contributor
There was a problem hiding this comment.
Please update args for image height and width, check and update args at other places also.
| Args: | ||
| image_url: URL or path to image | ||
| query: Text query to process with image | ||
| prompt = [query] |
| image = Image.open(requests.get(image_url, stream=True).raw) | ||
| else: | ||
| image = Image.open(image_url) | ||
| image = image.resize((536, 354)) |
Contributor
There was a problem hiding this comment.
we should check for self._image_height and self._image_width and if not passed then resize to these default shapes?
| else: | ||
| image = Image.open(image_url) | ||
|
|
||
| if "mistral3" in self._qeff_model.model.config.model_type: |
Contributor
There was a problem hiding this comment.
same as above. also please update the args for this function's docstrings.
| full_batch_size = 4 | ||
| queries = [query] * full_batch_size | ||
|
|
||
| pytorch_hf_tokens = [pytorch_hf_tokens] * 4 |
Contributor
There was a problem hiding this comment.
is there any reason we are not using run_vlm_hf_model_pytorch_CB here?
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.
Adding CB support for VLMs: