[PERF]support MERRouter #1421
Merged
[PERF]support MERRouter #1421
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
me
branch
5 times, most recently
from
de60ec9 to
a83a608
Compare
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #1421 +/- ##
==========================================
+ Coverage 27.39% 31.64% +4.24%
==========================================
Files 56 60 +4
Lines 6191 6640 +449
==========================================
+ Hits 1696 2101 +405
- Misses 4495 4539 +44
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
me
branch
2 times, most recently
from
ff174d1 to
4dd4478
Compare
Angazenn
force-pushed
the
me
branch
3 times, most recently
from
74f8b45 to
b1d95e6
Compare
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
47 tasks
Signed-off-by: angazenn <zengyanjia@huawei.com>
ganyi1996ppo
approved these changes
Jun 28, 2025
zhanghw0354
pushed a commit
to zhanghw0354/vllm-ascend
that referenced
this pull request
Jun 30, 2025
### What this PR does / why we need it? This PR introduces an expert rearrange algorithm for PanguProMoE model. Different from the original grouped topk, it filters out the top experts that are allocated more tokens. Therefore, we can load less experts when calculating gmm. We have test this algorithm for PanguProMoE-72B on 300I Duo platform and 800I A2 platform. On 300I Duo platform, we find that `num_voted_experts` set to 5 achieves both good performance and accuracy. While on 800I A2, we still set it to 8 to use original pangu grouped topk. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? <!-- CI passed with new added/existing test. If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future. If tests were not added, please describe why they were not added and/or why it was difficult to add. --> Signed-off-by: angazenn <zengyanjia@huawei.com> Co-authored-by: angazenn <zengyanjia@huawei.com> Signed-off-by: zhanghw0354 <zhanghaiwen_yewu@cmss.chinamobile.com>
weijinqian0
pushed a commit
to weijinqian0/vllm-ascend
that referenced
this pull request
Jun 30, 2025
### What this PR does / why we need it? This PR introduces an expert rearrange algorithm for PanguProMoE model. Different from the original grouped topk, it filters out the top experts that are allocated more tokens. Therefore, we can load less experts when calculating gmm. We have test this algorithm for PanguProMoE-72B on 300I Duo platform and 800I A2 platform. On 300I Duo platform, we find that `num_voted_experts` set to 5 achieves both good performance and accuracy. While on 800I A2, we still set it to 8 to use original pangu grouped topk. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? <!-- CI passed with new added/existing test. If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future. If tests were not added, please describe why they were not added and/or why it was difficult to add. --> Signed-off-by: angazenn <zengyanjia@huawei.com> Co-authored-by: angazenn <zengyanjia@huawei.com>
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Oct 16, 2025
### What this PR does / why we need it? This PR introduces an expert rearrange algorithm for PanguProMoE model. Different from the original grouped topk, it filters out the top experts that are allocated more tokens. Therefore, we can load less experts when calculating gmm. We have test this algorithm for PanguProMoE-72B on 300I Duo platform and 800I A2 platform. On 300I Duo platform, we find that `num_voted_experts` set to 5 achieves both good performance and accuracy. While on 800I A2, we still set it to 8 to use original pangu grouped topk. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? <!-- CI passed with new added/existing test. If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future. If tests were not added, please describe why they were not added and/or why it was difficult to add. --> Signed-off-by: angazenn <zengyanjia@huawei.com> Co-authored-by: angazenn <zengyanjia@huawei.com>
Angazenn
added a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
### What this PR does / why we need it? This PR introduces an expert rearrange algorithm for PanguProMoE model. Different from the original grouped topk, it filters out the top experts that are allocated more tokens. Therefore, we can load less experts when calculating gmm. We have test this algorithm for PanguProMoE-72B on 300I Duo platform and 800I A2 platform. On 300I Duo platform, we find that `num_voted_experts` set to 5 achieves both good performance and accuracy. While on 800I A2, we still set it to 8 to use original pangu grouped topk. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? <!-- CI passed with new added/existing test. If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future. If tests were not added, please describe why they were not added and/or why it was difficult to add. --> Signed-off-by: angazenn <zengyanjia@huawei.com> Co-authored-by: angazenn <zengyanjia@huawei.com>
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?
This PR introduces an expert rearrange algorithm for PanguProMoE model. Different from the original grouped topk, it filters out the top experts that are allocated more tokens. Therefore, we can load less experts when calculating gmm.
We have test this algorithm for PanguProMoE-72B on 300I Duo platform and 800I A2 platform. On 300I Duo platform, we find that
num_voted_expertsset to 5 achieves both good performance and accuracy. While on 800I A2, we still set it to 8 to use original pangu grouped topk.Does this PR introduce any user-facing change?
No.
How was this patch tested?