[Scheduler] Add AscendScheduler.#543
Merged
wangxiyuan merged 2 commits intovllm-project:mainfrom Apr 17, 2025
Merged
Conversation
whx-sjtu
force-pushed
the
add_ascend_scheduler
branch
5 times, most recently
from
5aaf864 to
462b4d7
Compare
added 2 commits
April 17, 2025 17:11
Signed-off-by: hw_whx <wanghexiang7@huawei.com>
Signed-off-by: hw_whx <wanghexiang7@huawei.com>
whx-sjtu
force-pushed
the
add_ascend_scheduler
branch
from
462b4d7 to
59f028f
Compare
wangxiyuan
approved these changes
Apr 17, 2025
| @@ -0,0 +1,396 @@ | |||
| # | |||
Collaborator
There was a problem hiding this comment.
move this file to singlecard folder, or update https://github.com/vllm-project/vllm-ascend/blob/main/.github/workflows/vllm_ascend_test.yaml#L124 to enable this test
| @@ -0,0 +1,73 @@ | |||
| # | |||
| # Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved. | |||
| # This file is a part of the vllm-ascend project. | |||
| # | ||
| # Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved. | ||
| # This file is a part of the vllm-ascend project. | ||
| # Adapted from vllm-project/vllm/blob/main/tests/models/utils.py |
Collaborator
|
This feature has been reviewd via 0.7.3-dev, i'll merge it now. Please fix the nit with a follow-up PR. Thanks. |
wangxiyuan
approved these changes
Apr 17, 2025
ttanzhiqiang
pushed a commit
to ttanzhiqiang/vllm-ascend
that referenced
this pull request
Apr 27, 2025
This PR adds AscendScheduler to vllm v1 engine. This scheduler currently supports v0-style prefill-first scheduling strategy. In the future more schedule methods will be supported by this scheduler. --------- Signed-off-by: hw_whx <wanghexiang7@huawei.com> Co-authored-by: hw_whx <wanghexiang7@huawei.com>
wangxiyuan
pushed a commit
that referenced
this pull request
Apr 29, 2025
### What this PR does / why we need it? Deepseek v3 now adopt vanilla chunked prefill on MLA part which is ineffcient for computing but necessary for chunked prefill. Since PR #543 bring v0 scheduler into vllm-ascend, we can now adopt torch_npu._npu_flash_attention inside the mla backend for more performance boost. Also there are some redundant computation inside the rope, which is also removed. This PR should bring some performance gain for deepseek eager mode inference. --------- Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Oct 16, 2025
…ct#598) ### What this PR does / why we need it? Deepseek v3 now adopt vanilla chunked prefill on MLA part which is ineffcient for computing but necessary for chunked prefill. Since PR vllm-project#543 bring v0 scheduler into vllm-ascend, we can now adopt torch_npu._npu_flash_attention inside the mla backend for more performance boost. Also there are some redundant computation inside the rope, which is also removed. This PR should bring some performance gain for deepseek eager mode inference. --------- Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
Angazenn
pushed a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
This PR adds AscendScheduler to vllm v1 engine. This scheduler currently supports v0-style prefill-first scheduling strategy. In the future more schedule methods will be supported by this scheduler. --------- Signed-off-by: hw_whx <wanghexiang7@huawei.com> Co-authored-by: hw_whx <wanghexiang7@huawei.com>
Angazenn
pushed a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
…ct#598) ### What this PR does / why we need it? Deepseek v3 now adopt vanilla chunked prefill on MLA part which is ineffcient for computing but necessary for chunked prefill. Since PR vllm-project#543 bring v0 scheduler into vllm-ascend, we can now adopt torch_npu._npu_flash_attention inside the mla backend for more performance boost. Also there are some redundant computation inside the rope, which is also removed. This PR should bring some performance gain for deepseek eager mode inference. --------- Signed-off-by: ganyi <pleaplusone.gy@gmail.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
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.
This PR adds AscendScheduler to vllm v1 engine.
This scheduler currently supports v0-style prefill-first scheduling strategy.
In the future more schedule methods will be supported by this scheduler.