[Scheduler][MTP] Add support for speculative decoding in AsecendScheduler.#943
Merged
ganyi1996ppo merged 8 commits intovllm-project:mainfrom Jun 11, 2025
Merged
Conversation
Contributor
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
whx-sjtu
force-pushed
the
adapt_ascend_scheduler_090
branch
from
7324819 to
08d08fa
Compare
whx-sjtu
force-pushed
the
adapt_ascend_scheduler_090
branch
from
08d08fa to
d1f53f8
Compare
whx-sjtu
changed the title
whx-sjtu
changed the title
whx-sjtu
force-pushed
the
adapt_ascend_scheduler_090
branch
3 times, most recently
from
e650a1d to
a543e1f
Compare
Contributor
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
whx-sjtu
force-pushed
the
adapt_ascend_scheduler_090
branch
from
a543e1f to
39d6cd1
Compare
whx-sjtu
force-pushed
the
adapt_ascend_scheduler_090
branch
2 times, most recently
from
efd6283 to
4b75f27
Compare
whx-sjtu
force-pushed
the
adapt_ascend_scheduler_090
branch
6 times, most recently
from
aa007f1 to
aa52202
Compare
Contributor
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
Signed-off-by: whx-sjtu <2952154980@qq.com>
Signed-off-by: whx-sjtu <2952154980@qq.com>
Signed-off-by: whx-sjtu <2952154980@qq.com>
Signed-off-by: whx-sjtu <2952154980@qq.com>
Signed-off-by: whx-sjtu <2952154980@qq.com>
Signed-off-by: whx-sjtu <2952154980@qq.com>
Signed-off-by: whx-sjtu <2952154980@qq.com>
whx-sjtu
force-pushed
the
adapt_ascend_scheduler_090
branch
from
feb3765 to
873f2c1
Compare
Signed-off-by: whx-sjtu <2952154980@qq.com>
ganyi1996ppo
approved these changes
Jun 11, 2025
Yikun
reviewed
Jun 11, 2025
Comment on lines
+188
to
+189
| # pytest -sv tests/singlecard/core/test_ascend_scheduler.py | ||
| # pytest -sv tests/singlecard/core/test_ascend_scheduler_e2e.py |
Member
There was a problem hiding this comment.
This PR drop the scheduler test, any plan to re-add? @ganyi1996ppo @whx-sjtu
Collaborator
Author
There was a problem hiding this comment.
This is because AscendScheduler is designed for v1, so I close ut of it in ci of v0.
Yikun
pushed a commit
that referenced
this pull request
Jun 12, 2025
momo609
pushed a commit
to momo609/vllm-ascend
that referenced
this pull request
Jun 17, 2025
…uler. (vllm-project#943) This PR adds support for speculative decoding in AsecendScheduler. Also inculde part of support for disaggregated prefill, full support will be merged in follow-up PR. --------- Signed-off-by: whx-sjtu <2952154980@qq.com>
momo609
pushed a commit
to momo609/vllm-ascend
that referenced
this pull request
Jun 17, 2025
…1180) Last PR [vllm-project#943 ](vllm-project#943) wrongly open ut of AscendScheduler in V0 ci, this PR fixes this problem and only run ut of it in V1 ci. Signed-off-by: whx-sjtu <2952154980@qq.com>
momo609
pushed a commit
to momo609/vllm-ascend
that referenced
this pull request
Jun 17, 2025
…uler. (vllm-project#943) This PR adds support for speculative decoding in AsecendScheduler. Also inculde part of support for disaggregated prefill, full support will be merged in follow-up PR. --------- Signed-off-by: whx-sjtu <2952154980@qq.com> Signed-off-by: wangxiaoxin (A) <wangxiaoxin7@huawei.com>
momo609
pushed a commit
to momo609/vllm-ascend
that referenced
this pull request
Jun 17, 2025
…1180) Last PR [vllm-project#943 ](vllm-project#943) wrongly open ut of AscendScheduler in V0 ci, this PR fixes this problem and only run ut of it in V1 ci. Signed-off-by: whx-sjtu <2952154980@qq.com> Signed-off-by: wangxiaoxin (A) <wangxiaoxin7@huawei.com>
momo609
pushed a commit
to momo609/vllm-ascend
that referenced
this pull request
Jun 17, 2025
…uler. (vllm-project#943) This PR adds support for speculative decoding in AsecendScheduler. Also inculde part of support for disaggregated prefill, full support will be merged in follow-up PR. --------- Signed-off-by: whx-sjtu <2952154980@qq.com> Signed-off-by: wangxiaoxin (A) <wangxiaoxin7@huawei.com>
momo609
pushed a commit
to momo609/vllm-ascend
that referenced
this pull request
Jun 17, 2025
…1180) Last PR [vllm-project#943 ](vllm-project#943) wrongly open ut of AscendScheduler in V0 ci, this PR fixes this problem and only run ut of it in V1 ci. Signed-off-by: whx-sjtu <2952154980@qq.com> Signed-off-by: wangxiaoxin (A) <wangxiaoxin7@huawei.com>
83 tasks
shiyuan680
pushed a commit
to raindaywhu/vllm-ascend
that referenced
this pull request
Jul 7, 2025
…uler. (vllm-project#943) This PR adds support for speculative decoding in AsecendScheduler. Also inculde part of support for disaggregated prefill, full support will be merged in follow-up PR. --------- Signed-off-by: whx-sjtu <2952154980@qq.com>
shiyuan680
pushed a commit
to raindaywhu/vllm-ascend
that referenced
this pull request
Jul 7, 2025
…1180) Last PR [vllm-project#943 ](vllm-project#943) wrongly open ut of AscendScheduler in V0 ci, this PR fixes this problem and only run ut of it in V1 ci. Signed-off-by: whx-sjtu <2952154980@qq.com>
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Oct 16, 2025
…uler. (vllm-project#943) This PR adds support for speculative decoding in AsecendScheduler. Also inculde part of support for disaggregated prefill, full support will be merged in follow-up PR. --------- Signed-off-by: whx-sjtu <2952154980@qq.com>
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Oct 16, 2025
…1180) Last PR [vllm-project#943 ](vllm-project#943) wrongly open ut of AscendScheduler in V0 ci, this PR fixes this problem and only run ut of it in V1 ci. Signed-off-by: whx-sjtu <2952154980@qq.com>
Angazenn
pushed a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
…uler. (vllm-project#943) This PR adds support for speculative decoding in AsecendScheduler. Also inculde part of support for disaggregated prefill, full support will be merged in follow-up PR. --------- Signed-off-by: whx-sjtu <2952154980@qq.com>
Angazenn
pushed a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
…1180) Last PR [vllm-project#943 ](vllm-project#943) wrongly open ut of AscendScheduler in V0 ci, this PR fixes this problem and only run ut of it in V1 ci. Signed-off-by: whx-sjtu <2952154980@qq.com>
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
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.
This PR adds support for speculative decoding in AsecendScheduler.
Also inculde part of support for disaggregated prefill, full support will be merged in follow-up PR.