[V0.7.3][LoRA][Qwen3] Make v0.7.3 support Qwen3+LoRA #1037
Merged
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
Signed-off-by: paulyu <[email protected]>
paulyu12
changed the title
paulyu12
changed the title
added 3 commits
May 30, 2025 23:33
Signed-off-by: paulyu <[email protected]>
Signed-off-by: paulyu <[email protected]>
Signed-off-by: paulyu <[email protected]>
Collaborator
|
Thanks for the update! We can merge this first. While we don't have the detail plan for post2 release. Maybe it needs more time. |
wangxiyuan
approved these changes
Jun 3, 2025
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Outdated suggestions cannot be applied.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.
What this PR does / why we need it?
Because the EOL vLLM-v0.7.3 lacks this PR(vllm-project/vllm#13166), while launching Qwen3+LoRA on vllm-ascend0.7.3, the error "Qwen3ForCausalLM" object has no attribute "embedding modules" will be raised.
We modify qwen3.py to support Qwen3+LoRA on vllm-ascend v0.7.3 instead.
Does this PR introduce any user-facing change?
No.
How was this patch tested?