Bugfix_091dev_OOM #2910
Open
Bugfix_091dev_OOM #2910
+14
−2
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
Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request aims to fix an out-of-memory error on decoder nodes by reducing the chunked_prefill_workspace_size. The change correctly identifies the consumer node and applies a smaller limit. However, the implementation for the consumer node is unnecessarily complex. I've provided a suggestion to simplify the logic, which makes the code more readable and maintainable while achieving the same result.
momo609
reviewed
Sep 14, 2025
| if vllm_config.kv_transfer_config.is_kv_consumer: | ||
| max_chunked_size = scheduler_config.max_num_seqs * self.block_size | ||
| else: | ||
| max_chunked_size = 128 * 1024 |
There was a problem hiding this comment.
const variables should be defined at the front of file with bigger case, and don't forget to note it also.
weijinqian0
reviewed
Sep 14, 2025
| self.chunked_prefill_enabled = scheduler_config.chunked_prefill_enabled | ||
| if self.chunked_prefill_enabled: | ||
| if vllm_config.kv_transfer_config.is_kv_consumer: | ||
| max_chunked_size = scheduler_config.max_num_seqs * self.block_size |
There was a problem hiding this comment.
Is the OOM caused by the batch size being greater than 1024?
Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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?
Resolving the issue of the chunked work size being too large, which leads to D node out-of-memory (OOM) errors.
Does this PR introduce any user-facing change?
no
How was this patch tested?
by ci