refactor linear #2867
Merged
refactor linear #2867
+688
−503
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
|
👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:
If CI fails, you can run linting and testing checks locally according Contributing and Testing. |
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
|
Warning Gemini encountered an error creating the review. You can try again by commenting |
realliujiaxu
force-pushed
the
refactor_linear
branch
from
4b069b1 to
541645c
Compare
|
We have discussed a refactoring plan that will encapsulate the differing parts while keeping the patch sections unchanged. |
realliujiaxu
force-pushed
the
refactor_linear
branch
2 times, most recently
from
5999110 to
5e45c5d
Compare
|
@weijinqian0 This PR is ready for review now |
realliujiaxu
force-pushed
the
refactor_linear
branch
from
81c6988 to
61bae75
Compare
realliujiaxu
force-pushed
the
refactor_linear
branch
from
e665f8e to
6e872e7
Compare
Signed-off-by: realliujiaxu <realliujiaxu@163.com> Co-authored-by: weijinqian0 <weijinqian@huawei.com>
Signed-off-by: realliujiaxu <realliujiaxu@163.com>
Signed-off-by: realliujiaxu <realliujiaxu@163.com>
realliujiaxu
force-pushed
the
refactor_linear
branch
from
6e872e7 to
3ff6204
Compare
momo609
reviewed
Sep 16, 2025
Signed-off-by: realliujiaxu <realliujiaxu@163.com>
Signed-off-by: realliujiaxu <realliujiaxu@163.com>
Signed-off-by: realliujiaxu <realliujiaxu@163.com>
|
approved |
wangxiyuan
added
ready
wangxiyuan
approved these changes
Sep 18, 2025
| 3. Override the apply method according to requirements, which will replace the original linear.forward | ||
| 4. Add selection logic for MyColumnParallelOp in the get_column_parallel_op method, typically based on prefix and configuration judgments | ||
| Row parallel op follows a similar approach - inherit from RowColumnParallelOp and register the new class in get_row_parallel_op. | ||
| """ |
wangxiyuan
approved these changes
Sep 18, 2025
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?
The current linear.py has the following issues:
There is redundant conditional logic in the
comm_groupandforwardselection for classes such asAscendMergedColumnParallelLinear.Inconsistent comm_group selection logic exists among
AscendMergedColumnParallelLinear,AscendColumnParallelLinear, andAscendQKVParallelLinear.To address these two issues, this PR encapsulates
comm_groupandforwardinto classes and extracts the classes selection logic into common functions. For future additions of custom communication groups or forward methods, it will only be necessary to extendCustomColumnParallelOporCustomRowParallelOpand add new selection logic.Does this PR introduce any user-facing change?
No
How was this patch tested?