biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Attention][1/n] Remove usage of deprecated seq_lens_cpu and num_computed_tokens_cpu CommonAttentionMetadata properties (#31773)

Browse Source 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
This commit is contained in:
Lucas Wilkinson
2026-01-06 07:05:17 -05:00
committed by GitHub
parent 14df02b4e1
commit e0327c9db2
9 changed files with 23 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/v1/attention/test_sparse_mla_backends.py
View File

@@ -297,7 +297,7 @@ def test_sparse_backend_decode_correctness(
positions = np.arange(starts[-1], dtype=np.int32) - np.repeat(
starts[:-1], seg_lengths
)
seq_lengths = np.asarray(common_attn_metadata.seq_lens_cpu, dtype=np.int32)
seq_lengths = np.asarray(common_attn_metadata.seq_lens.cpu(), dtype=np.int32)
prefix_lengths = seq_lengths - seg_lengths
positions += np.repeat(prefix_lengths, seg_lengths)