[Fix] Set default values to fix spec decode #1105
Closed
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
wangxiyuan
approved these changes
Jun 6, 2025
MengqingCao
added
long-term-test
mengwei805
approved these changes
Jun 6, 2025
mengwei805
reviewed
Jun 6, 2025
| draft_worker_kwargs[ | ||
| "vllm_config"].parallel_config.expert_parallel_size = 1 | ||
| draft_worker_kwargs[ | ||
| "vllm_config"].parallel_config.expert_tensor_parallel_size = 1 |
Collaborator
There was a problem hiding this comment.
i see CI was failed
maybe can make
draft_worker_kwargs[
"vllm_config"].parallel_config.expert_parallel_size = 1
draft_worker_kwargs[
"vllm_config"].parallel_config.expert_tensor_parallel_size = 1
to line 59
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
Co-authored-by: mengwei805 <mengwei25@huawei.com> Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
Collaborator
|
If CI failed due to OOM, this PR fixed: #1109 |
Yuxiao-Xu
pushed a commit
to Yuxiao-Xu/vllm-ascend
that referenced
this pull request
Jun 7, 2025
…ard CI (vllm-project#1109) ### What this PR does / why we need it? - Set default values to fix spec decode - To avoid oom, we need to run the test in a single process ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? - CI passed, espcecially multicards CI - For spec decode test, long term CI passed Closes: vllm-project#1105 --------- Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com> Signed-off-by: Yikun Jiang <yikunkero@gmail.com> Co-authored-by: Yizhou Liu <liu_yizhou@outlook.com> Co-authored-by: mengwei805 <mengwei25@huawei.com>
Yuxiao-Xu
pushed a commit
to Yuxiao-Xu/vllm-ascend
that referenced
this pull request
Jun 7, 2025
…ard CI (vllm-project#1109) ### What this PR does / why we need it? - Set default values to fix spec decode - To avoid oom, we need to run the test in a single process ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? - CI passed, espcecially multicards CI - For spec decode test, long term CI passed Closes: vllm-project#1105 --------- Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com> Signed-off-by: Yikun Jiang <yikunkero@gmail.com> Co-authored-by: Yizhou Liu <liu_yizhou@outlook.com> Co-authored-by: mengwei805 <mengwei25@huawei.com>
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Oct 16, 2025
…ard CI (vllm-project#1109) ### What this PR does / why we need it? - Set default values to fix spec decode - To avoid oom, we need to run the test in a single process ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? - CI passed, espcecially multicards CI - For spec decode test, long term CI passed Closes: vllm-project#1105 --------- Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com> Signed-off-by: Yikun Jiang <yikunkero@gmail.com> Co-authored-by: Yizhou Liu <liu_yizhou@outlook.com> Co-authored-by: mengwei805 <mengwei25@huawei.com>
Angazenn
pushed a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
…ard CI (vllm-project#1109) ### What this PR does / why we need it? - Set default values to fix spec decode - To avoid oom, we need to run the test in a single process ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? - CI passed, espcecially multicards CI - For spec decode test, long term CI passed Closes: vllm-project#1105 --------- Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com> Signed-off-by: Yikun Jiang <yikunkero@gmail.com> Co-authored-by: Yizhou Liu <liu_yizhou@outlook.com> Co-authored-by: mengwei805 <mengwei25@huawei.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?
Set default values to fix spec decode
Does this PR introduce any user-facing change?
How was this patch tested?