[DP][V1] Fix rank set in DP scenario & Bump torch-npu version to 2.5.1.post1.dev20250528 #1235
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
|
This should be merged after #884 |
|
I like the PR which remove the patch code. Let's merge this asap. |
realliujiaxu
approved these changes
Jun 16, 2025
MengqingCao
force-pushed
the
dpfix
branch
2 times, most recently
from
6f48563 to
a92e5fb
Compare
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
github-actions
bot
added
documentation
Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: Icey <1790571317@qq.com> Signed-off-by: MengqingCao <cmq0113@163.com>
83 tasks
Yikun
changed the title
MengqingCao
changed the title
Yikun
approved these changes
Jun 16, 2025
Yikun
added
long-term-test
ganyi1996ppo
pushed a commit
that referenced
this pull request
Jun 17, 2025
… to 2.5.1.post1.dev20250528 (#1247) ### What this PR does / why we need it? Cherry-pick form #1235 1. Fix rank set in DP scenario. The new poc version of torch-npu support setting `ASCEND_RT_VISIBLE_DEVICES` dynamically, thus we could use the rank set in `DPEngineCoreProc` directly instead of calculating local rank across dp by hand in the patched `_init_data_parallel` Closes: #1170 2. Bump torch-npu version to 2.5.1.post1.dev20250528 Closes: #1242 Closes: #1232 ### How was this patch tested? CI passed with new added test. --------- Signed-off-by: Icey <1790571317@qq.com> Signed-off-by: MengqingCao <cmq0113@163.com> Co-authored-by: Icey <1790571317@qq.com>
Yikun
added a commit
to Yikun/vllm-ascend
that referenced
this pull request
Jun 21, 2025
… to 2.5.1.post1.dev20250528 (vllm-project#1235)" This reverts commit 96fa7ff.
shiyuan680
pushed a commit
to raindaywhu/vllm-ascend
that referenced
this pull request
Jul 7, 2025
…1.post1.dev20250528 (vllm-project#1235) 1. Fix rank set in DP scenario. The new poc version of torch-npu support setting `ASCEND_RT_VISIBLE_DEVICES` dynamically, thus we could use the rank set in `DPEngineCoreProc` directly instead of calculating local rank across dp by hand in the patched `_init_data_parallel` Closes: vllm-project#1170 2. Bump torch-npu version to 2.5.1.post1.dev20250528 Closes: vllm-project#1242 Closes: vllm-project#1232 CI passed with new added test. --------- Signed-off-by: MengqingCao <cmq0113@163.com> Signed-off-by: Icey <1790571317@qq.com> Co-authored-by: Icey <1790571317@qq.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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?
ASCEND_RT_VISIBLE_DEVICESdynamically, thus we could use the rank set inDPEngineCoreProcdirectly instead of calculating local rank across dp by hand in the patched_init_data_parallelCloses: #1170
Closes: #1242
Closes: #1232
How was this patch tested?
CI passed with new added test.