Reranker & Embedding: single-QPC support with KV cache eliminated#1045
Open
quic-amitraj wants to merge 1 commit into
Open
Reranker & Embedding: single-QPC support with KV cache eliminated#1045quic-amitraj wants to merge 1 commit into
quic-amitraj wants to merge 1 commit into
Conversation
quic-amitraj
changed the title
quic-amitraj
force-pushed
the
reranker_single_qpc
branch
from
52be851 to
3941ee0
Compare
quic-amitraj
force-pushed
the
reranker_single_qpc
branch
3 times, most recently
from
d484b02 to
b265e87
Compare
quic-amitraj
force-pushed
the
reranker_single_qpc
branch
2 times, most recently
from
dea8b26 to
a7f8f9e
Compare
quic-rishinr
force-pushed
the
release/v1.22.0_tmp
branch
2 times, most recently
from
8273e7f to
e9330a8
Compare
quic-amitraj
force-pushed
the
reranker_single_qpc
branch
4 times, most recently
from
1920a28 to
86dd92a
Compare
| "additional_params": {} | ||
| }, | ||
| { | ||
| "model_name": "Qwen/Qwen3-VL-Reranker-8B", |
Contributor
There was a problem hiding this comment.
update to dummy models
| @@ -0,0 +1,28 @@ | |||
| [ | |||
| { | |||
| "model_name": "Qwen/Qwen3-VL-Reranker-2B", | |||
Contributor
There was a problem hiding this comment.
update to dummy models
quic-amitraj
force-pushed
the
reranker_single_qpc
branch
2 times, most recently
from
87f95d6 to
8ed9fda
Compare
Signed-off-by: Amit Raj <amitraj@qti.qualcomm.com>
quic-amitraj
force-pushed
the
reranker_single_qpc
branch
from
8ed9fda to
468df71
Compare
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This PR finalizes the Qwen3-VL reranker/embedding single-QPC flow and validation updates:
kv_offload=False) for reranker/embedding use cases.Validation Environment
qwen-vl-utils:0.0.14Example Validation Results
examples/embeddings/qwen3vl/qwen3_vl_embedding.pyQwen/Qwen3-VL-Embedding-8Bexamples/reranker/qwen3vl/qwen3_vl_reranker.pyQwen/Qwen3-VL-Reranker-2Bexamples/reranker/qwen3vl/qwen3_vl_reranker.pyQwen/Qwen3-VL-Reranker-8B