fix kernel block size, port of #1439#1453
Merged
Merged
Conversation
Signed-off-by: Iryna Boiko <iboiko@habana.ai>
iboiko-habana
requested review from
PatrykWo,
adobrzyn,
afierka-intel,
jbyczkow,
kamil-kaczor,
ksmusz,
mgawarkiewicz-intel,
michalkuligowski and
xuechendi
as code owners
Contributor
There was a problem hiding this comment.
Pull request overview
This PR updates the V1 HPU attention backend’s supported kernel block sizes to include 16-token blocks while preserving the existing 128/528/768-token support used by standard HPU and Granite hybrid configurations.
Changes:
- Adds 16 to
HPUAttentionBackendV1.get_supported_kernel_block_sizes(). - Updates the inline comment to describe the new smaller/testing block-size support.
kamil-kaczor
approved these changes
May 18, 2026
✅ CI PassedAll checks passed successfully against the following vllm commit: |
iboiko-habana
added a commit
that referenced
this pull request
May 19, 2026
1) added in #1453 16 is supported for testing/smaller models; 128 is the standard HPU kernel block size; 528 is required for Granite 4.0-H (granitemoehybrid) without prefix caching (16-token FA alignment), 768 with prefix caching (chunk-aligned). 2) _patch_hf3fs_mock_client_for_cpu_only Upstream mock client unconditionally calls ``torch.cuda.current_stream().wait_event(event)`` in ``batch_write``. In environments where PyTorch is not compiled with CUDA, that path throws and the method returns ``-1`` for writes, causing connector unit tests to fail. This patch keeps the same behavior but skips CUDA synchronization when CUDA is unavailable. --------- Signed-off-by: Harish Subramony <harish.subramony@intel.com> Co-authored-by: Iryna Boiko <iryna.boiko@intel.com>
mgawarkiewicz-intel
pushed a commit
that referenced
this pull request
May 25, 2026
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
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.
Port of #1439
16 is supported for testing/smaller models; 128 is the standard HPU
kernel block size; 528 is required for Granite 4.0-H
(granitemoehybrid) without prefix caching (16-token FA alignment),
768 with prefix caching (chunk-aligned).