[0.9.1][BugFix]fix accuracy in dbo after refactor MOE #1328
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
shikang-hangzhou
changed the title
Signed-off-by: shikang-hangzhou <459956190@qq.com>
shikang-hangzhou
changed the title
wangxiyuan
approved these changes
Jun 21, 2025
22dimensions
pushed a commit
to 22dimensions/vllm-ascend
that referenced
this pull request
Jul 22, 2025
…llm-project#1328) Fix accuracy problem after MOE refactor and make inference flow better. None e2e test in `tests/e2e/multicard/test_offline_inference_distributed.py` Signed-off-by: shikang-hangzhou <459956190@qq.com>
22dimensions
pushed a commit
to 22dimensions/vllm-ascend
that referenced
this pull request
Jul 22, 2025
…m-project#1420 vllm-project#1328 from v0.9.1-dev to main Signed-off-by: 22dimensions <waitingwind@foxmail.com>
22dimensions
pushed a commit
to 22dimensions/vllm-ascend
that referenced
this pull request
Jul 23, 2025
…m-project#1420 vllm-project#1328 from v0.9.1-dev to main Signed-off-by: 22dimensions <waitingwind@foxmail.com>
venus-taibai
pushed a commit
to venus-taibai/vllm-ascend
that referenced
this pull request
Sep 17, 2025
Merge branch zxdu/dev-v0.9.1.0622-dbo-prefill of git@code.alipay.com:Theta/vllm-ascend.git into dev-v0.9.1.0622 https://code.alipay.com/Theta/vllm-ascend/pull_requests/187 Reviewed-by: 沧濯 <zhengshoujian.zsj@antgroup.com> * [0.9.1][Bugfix] fix dp error in dbo (vllm-project#1291) * [0.9.1][BugFix]fix accuracy in dbo after refactor MOE (vllm-project#1328) * [feat]: sync with deepseekv2 * [feat]: support chunked prefill split for dbo * [fix]: overlap shared experts with post layernorm * support fused_moe_allgather_ep * [feat]: dbo support allgather ep * [fix]: revert changes to format
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?
Fix accuracy problem after MOE refactor and make inference flow better.
Does this PR introduce any user-facing change?
None
How was this patch tested?
e2e test in
tests/e2e/multicard/test_offline_inference_distributed.py