Added support for InternVL_3_5 series of VLMs. #566
+591
−199
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
Added support for Qwen3ForCausalLM models, tested on Qwen3-0.6B model for CI runs. Updated modeling internvl script to allow proper prefix chunking of vision+embeds when more than 1 patches are needed. Test InternVL_3_5_1B model for 1 and full layers via CI. Signed-off-by: quic-dhirajku <[email protected]>
quic-dhirajku
requested review from
quic-rishinr,
ochougul,
quic-hemagnih and
quic-amitraj
as code owners
Updated internvl_inference script to allow easy batch inference and compilation. This method supports single prompt single image batching method as originally supported by the model and in the same template. Signed-off-by: quic-dhirajku <[email protected]>
…ernVL models. Signed-off-by: quic-dhirajku <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Added support for Qwen3ForCausalLM models, tested on Qwen3-0.6B model for CI runs. Updated modeling internvl script to allow proper prefix chunking of vision+embeds when more than 1 patches are needed. Test InternVL_3_5_1B model for 1 and full layers via CI.