fix torchair execute issue on padding data, and mtp padding logic #1160
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: ganyi <pleaplusone.gy@gmail.com>
|
This PR also add the padding support for mtp + torchair case |
wangxiyuan
approved these changes
Jun 10, 2025
|
Let's add the test later |
wangxiyuan
added a commit
to wangxiyuan/vllm-ascend
that referenced
this pull request
Jun 12, 2025
…ogic (vllm-project#1160)" This reverts commit 291c216.
wangxiyuan
added a commit
to wangxiyuan/vllm-ascend
that referenced
this pull request
Jun 12, 2025
…ogic (vllm-project#1160)" This reverts commit 291c216.
wangxiyuan
added a commit
to wangxiyuan/vllm-ascend
that referenced
this pull request
Jun 13, 2025
…ogic (vllm-project#1160)" This reverts commit 291c216. Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
shiyuan680
pushed a commit
to raindaywhu/vllm-ascend
that referenced
this pull request
Jul 7, 2025
…lm-project#1160) The former PR vllm-project#736 select the valid token inside the `input_ids` and `position_ids` breaks the necessary padding required by torchair. In this PR, we pending the pad logic after the multimodal part. Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
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Outdated suggestions cannot be applied.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 former PR #736 select the valid token inside the
input_idsandposition_idsbreaks the necessary padding required by torchair. In this PR, we pending the pad logic after the multimodal part.Does this PR introduce any user-facing change?
How was this patch tested?