[main] Use AddRmsNormQuant ops in the custom model to optimize Qwen3's performance #1806
+227
−8
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
rjg-lyh
force-pushed
the
pr-addrmsnorm-main
branch
2 times, most recently
from
6ee87ad to
3ee0a48
Compare
Codecov ReportAttention: Patch coverage is
❌ Your patch check has failed because the patch coverage (49.38%) is below the target coverage (100.00%). You can increase the patch coverage or adjust the target coverage. Additional details and impacted files@@ Coverage Diff @@
## main #1806 +/- ##
==========================================
- Coverage 54.93% 54.86% -0.07%
==========================================
Files 80 81 +1
Lines 9712 9789 +77
==========================================
+ Hits 5335 5371 +36
- Misses 4377 4418 +41
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
wangxiyuan
reviewed
Jul 16, 2025
| @@ -0,0 +1,156 @@ | |||
| from collections.abc import Iterable | |||
There was a problem hiding this comment.
do not rewrite the model arch, if the change is only AddRMSNormW8A8Quant.
From 0.9.2, vllm support custom ops override, we can register our ops when setup vllm-ascend, take #1647 for example.
rjg-lyh
force-pushed
the
pr-addrmsnorm-main
branch
from
3ee0a48 to
b50de2c
Compare
…s performance Signed-off-by: rjg-lyh <1318825571@qq.com>
rjg-lyh
force-pushed
the
pr-addrmsnorm-main
branch
from
b50de2c to
1b0e244
Compare
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Outdated suggestions cannot be applied.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.
What this PR does / why we need it?
Optimizes the performance of the Qwen3 quantization model by registering a custom model and adding the AddRmsNormQuant operation. Subsequent PRs will focus on performance optimizations based on this custom model.
Does this PR introduce any user-facing change?
No.
How was this patch tested?
CI passed with existing test.