Skip to content

[bugfix] ascend schedule encountered an incorrect req block length in… #2429

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

[bugfix] ascend schedule encountered an incorrect req block length in… #2429

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1ff20d1
[bugfix] ascend schedule encountered an incorrect req block length in…
liziyu179 Aug 19, 2025
4eb9e06
Merge branch 'vllm-project:main' into main
liziyu179 Aug 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion vllm_ascend/core/scheduler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -444,7 +444,7 @@ def _check_watermark_for_prefill(self,
self.block_size)
req_blocks = self.kv_cache_manager.coordinator.get_blocks(
request.request_id)
num_new_blocks = (num_required_blocks - len(req_blocks) -
num_new_blocks = (num_required_blocks - len(req_blocks[0]) -
len(computed_blocks))
Comment on lines 445 to 448
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

critical

The change from len(req_blocks) to len(req_blocks[0]) is conceptually correct for getting the number of allocated blocks. However, the current implementation is not robust and can lead to runtime errors:

  1. self.kv_cache_manager.coordinator.get_blocks(request.request_id) will raise a KeyError if a request has no blocks allocated yet, which is the case for new requests from the waiting queue.
  2. If get_blocks were to return an empty list for a new request, req_blocks[0] would then raise an IndexError.

This can cause the scheduler to crash. The implementation should be updated to handle these cases gracefully.

        req_blocks = self.kv_cache_manager.coordinator.req_to_blocks.get(
            request.request_id, [])
        num_allocated_blocks = len(req_blocks[0]) if req_blocks else 0
        num_new_blocks = (num_required_blocks - num_allocated_blocks -
                          len(computed_blocks))

num_evictable_computed_blocks = sum(1 for blk in computed_blocks
if blk.ref_cnt == 0)
Expand Down
Loading