Jonas M. Kübler 98e7f223b9 enable skipping of SW attention layers when using FP8 KV cache (#33695) ...

Signed-off-by: Jonas Kuebler <kuebj@amazon.com>

2026-03-27 07:25:02 -06:00

..

__init__.py

[5/N][Attention] Finish eliminating vllm/attention folder (#32064)

2026-01-27 10:02:51 -05:00

attention.py

enable skipping of SW attention layers when using FP8 KV cache (#33695)

2026-03-27 07:25:02 -06:00

chunked_local_attention.py

Reapply [Attention] Refactor check_and_update_config (#35122)

2026-03-09 07:17:14 -07:00

cross_attention.py

Reapply [Attention] Refactor check_and_update_config (#35122)

2026-03-09 07:17:14 -07:00

encoder_only_attention.py

Reapply [Attention] Refactor check_and_update_config (#35122)

2026-03-09 07:17:14 -07:00

kv_transfer_utils.py

[ROCm] AITER fused RoPE+KVCache (#33443)

2026-02-23 19:06:00 -08:00

mla_attention.py

[XPU] support MLA model on Intel GPU (#37143)

2026-03-25 17:43:42 +08:00

mm_encoder_attention.py

[Log] Reduce duplicate log (#37313)

2026-03-18 10:57:44 -04:00

static_sink_attention.py

[V0 Deprecation] Refactor kv cache from list to element (#37487)

2026-03-23 20:10:11 -07:00