Draft
Conversation
qcdipankar
requested review from
ochougul,
quic-amitraj,
quic-hemagnih and
quic-rishinr
as code owners
qcdipankar
force-pushed
the
qwen3_vl_mainline
branch
4 times, most recently
from
5bc0eb7 to
19a163b
Compare
quic-rishinr
requested changes
Mar 3, 2026
examples/image_text_to_text/models/qwen3_vl_moe/qwen3_vl_disagg_mode.py
Outdated
Show resolved
Hide resolved
ochougul
reviewed
Mar 3, 2026
examples/image_text_to_text/models/qwen3_vl_moe/qwen3_vl_moe_continous_batching.py
Show resolved
Hide resolved
anujgupt-github
requested changes
Mar 3, 2026
examples/image_text_to_text/models/qwen3_vl_moe/qwen3_vl_moe_contnious_batching.py
Outdated
Show resolved
Hide resolved
| height=354, | ||
| width=536, | ||
| mxfp6_matmul=True, | ||
| mxint8_kv_cache=True, |
Contributor
There was a problem hiding this comment.
Subfunction infra support is available, we can add that flag in compile api. I added in MOE examples. @qcdipankar could you pls update here too
| if output_name.endswith("_RetainedState"): | ||
| custom_io_lang[output_name[: -len("_RetainedState")]] = ( | ||
| "float16" if "vision_embeds" in output_name else kv_cache_dtype | ||
| "float16" |
Contributor
There was a problem hiding this comment.
can you take it from a top level argument passed from pretrained()
ochougul
requested changes
Mar 10, 2026
qcdipankar
force-pushed
the
qwen3_vl_mainline
branch
from
251c3bc to
be48dcf
Compare
Signed-off-by: Dipankar Sarkar <quic_dipankar@quicinc.com> Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com> Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com> Co-authored-by: Dipankar Sarkar <dipankar@qti.qualcomm.com> Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com> Signed-off-by: Dipankar Sarkar <quic_dipankar@quicinc.com> Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com> Signed-off-by: Dhiraj Kumar Sah <dhirajku@qti.qualcomm.com> Co-authored-by: Dipankar Sarkar <dipankar@qti.qualcomm.com> Co-authored-by: Onkar Chougule <168134249+ochougul@users.noreply.github.com> Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
The Onboarding of Qwen3VlMoe --------- Signed-off-by: Dipankar Sarkar <quic_dipankar@quicinc.com> Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com> Signed-off-by: vtirumal <vtirumal@qti.qualcomm.com> Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com> Co-authored-by: vtirumal <vtirumal@qti.qualcomm.com> Co-authored-by: Onkar Chougule <168134249+ochougul@users.noreply.github.com> Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <quic_dipankar@quicinc.com> Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com> Signed-off-by: vtirumal <vtirumal@qti.qualcomm.com> Co-authored-by: Dipankar Sarkar <dipankar@qti.qualcomm.com> Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Added Support for Subfn for Qwen 3 VL dense, MOE. Updated prefill only logic for disagg mode --------- Signed-off-by: vtirumal <vtirumal@qti.qualcomm.com> Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
qcdipankar
force-pushed
the
qwen3_vl_mainline
branch
from
46d18ab to
47dd748
Compare
#849) Signed-off-by: vtirumal <vtirumal@qti.qualcomm.com>
qcdipankar
force-pushed
the
qwen3_vl_mainline
branch
from
3dab4b6 to
6598856
Compare
Signed-off-by: Dipankar Sarkar <dipankar@qti.qualcomm.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 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.