Lucas Wilkinson 9fec0e13d5 [Attention] Cache attention metadata builds across hybrid KV-cache groups (#29627) ...

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Stanislaw Wozniak <stw@zurich.ibm.com>

2025-12-16 17:10:16 -05:00

..

test_attention_backends_selection.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_attention_backends.py

[v1] Add real sliding window calculation to FlexAttention direct BlockMask building (#26015)

2025-12-01 13:12:51 +00:00

test_attention_splitting.py

[feature] extend DBO to XBO (#30120)

2025-12-16 00:04:01 -05:00

test_batch_reordering.py

[BugFix] Reordering extend logic fix (#27739)

2025-10-29 21:39:34 -07:00

test_chunked_local_attention.py

[Attention] Cache attention metadata builds across hybrid KV-cache groups (#29627)

2025-12-16 17:10:16 -05:00

test_mla_backends.py

[Attention] Refactor FA block_size limitations to hybrid models only (#29084)

2025-11-22 06:38:44 -08:00

test_rocm_attention_backends_selection.py

[Attention] Update attention imports (#29540)

2025-11-27 11:19:09 -05:00

test_sparse_mla_backends.py

[Attention] Use sparse prefill kernel for fp8 kv-cache in DeepSeek-v3.2 (#27532)

2025-12-12 05:57:47 -08:00

utils.py

[Attention] Make seq_lens_cpu optional in CommonAttentionMetadata to enable true async spec-decode (#29624)

2025-12-09 17:18:10 -08:00