[CORE]initial support for torchair with non-mla backend #1506
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
Angazenn
force-pushed
the
torchair
branch
4 times, most recently
from
f32a5e3 to
d8c7ecd
Compare
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #1506 +/- ##
===========================================
+ Coverage 27.39% 51.60% +24.20%
===========================================
Files 56 78 +22
Lines 6191 9474 +3283
===========================================
+ Hits 1696 4889 +3193
- Misses 4495 4585 +90
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:
|
Angazenn
force-pushed
the
torchair
branch
6 times, most recently
from
88cd32f to
31f0d92
Compare
Angazenn
force-pushed
the
torchair
branch
2 times, most recently
from
7427ef8 to
571ba99
Compare
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
Angazenn
force-pushed
the
torchair
branch
4 times, most recently
from
c4a7f85 to
c5a9254
Compare
github-actions
bot
added
the
documentation
Angazenn
changed the title
Angazenn
force-pushed
the
torchair
branch
3 times, most recently
from
83e54bc to
a88bd2c
Compare
47 tasks
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
Angazenn
force-pushed
the
torchair
branch
4 times, most recently
from
ad27bb9 to
62998bb
Compare
wangxiyuan
approved these changes
Jul 3, 2025
Collaborator
wangxiyuan
left a comment
wangxiyuan
left a comment
There was a problem hiding this comment.
TODO:
move all torchair attention code to attention_v1_torchiar in the future
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: tianyitang <tangtianyi4@huawei.com>
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: tianyitang <tangtianyi4@huawei.com>
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Oct 16, 2025
…#1506) ### What this PR does / why we need it? This PR supports torchair graph mode with non-mla backend on both 800IA2 and 300I Duo platforms. The main change is to add `attention_v1_torchair.py` to support specific attention related operations that are required by torchair. ### Does this PR introduce _any_ user-facing change? Before this PR, vLLM-Ascend only allows deepseek to use torchair. Now we can also use it with pangu. Besides, we add a support model list to control which type of models that can use torchair. ### How was this patch tested? We have test it with PanguProMoE on both 800IA2 and 300I Duo platforms, and model generates answer normally. --------- Signed-off-by: angazenn <zengyanjia@huawei.com> Signed-off-by: tianyitang <tangtianyi4@huawei.com> Co-authored-by: angazenn <zengyanjia@huawei.com> Co-authored-by: tianyitang <tangtianyi4@huawei.com>
Angazenn
added a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
…#1506) ### What this PR does / why we need it? This PR supports torchair graph mode with non-mla backend on both 800IA2 and 300I Duo platforms. The main change is to add `attention_v1_torchair.py` to support specific attention related operations that are required by torchair. ### Does this PR introduce _any_ user-facing change? Before this PR, vLLM-Ascend only allows deepseek to use torchair. Now we can also use it with pangu. Besides, we add a support model list to control which type of models that can use torchair. ### How was this patch tested? We have test it with PanguProMoE on both 800IA2 and 300I Duo platforms, and model generates answer normally. --------- Signed-off-by: angazenn <zengyanjia@huawei.com> Signed-off-by: tianyitang <tangtianyi4@huawei.com> Co-authored-by: angazenn <zengyanjia@huawei.com> Co-authored-by: tianyitang <tangtianyi4@huawei.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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?
This PR supports torchair graph mode with non-mla backend on both 800IA2 and 300I Duo platforms. The main change is to add
attention_v1_torchair.pyto support specific attention related operations that are required by torchair.Does this PR introduce any user-facing change?
Before this PR, vLLM-Ascend only allows deepseek to use torchair. Now we can also use it with pangu. Besides, we add a support model list to control which type of models that can use torchair.
How was this patch tested?
We have test it with PanguProMoE on both 800IA2 and 300I Duo platforms, and model generates answer normally.