Skip to content

vllm_omni.diffusion.attention.parallel.allgather_kv ¶

AllGatherKVParallelAttention ¶

Compute local Q against AllGathered K/V.

enabled `property` ¶

enabled: bool

name `property` ¶

name: str

post_attention ¶

post_attention(
    attn_output: Tensor,
    ctx: ParallelAttentionContext | None,
) -> Tensor

pre_attention ¶

pre_attention(
    query: Tensor,
    key: Tensor,
    value: Tensor,
    attn_metadata: AttentionMetadata | None,
)