[FEAT]Add FastVideo VSA backend for Wan2.2 (#4820)

Signed-off-by: bjf-frz <frz123db@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
bjf-frzandHongsheng Liu authored and GitHub committed 2026-08-24 14:48:31 +08:00
1 parent 3d035bfa19
commit 072bfc02dd
28 files changed
+1316 -107

No files matched your search

@@ -1,5 +1,5 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
"""Diffusion attention backend registry.
This module provides an enum-based registry for diffusion attention backends,
@@ -23,7 +23,7 @@ logger = init_logger(__name__)
class _DiffusionBackendEnumMeta(EnumMeta):
"""Metaclass for DiffusionAttentionBackendEnum to provide better error messages."""
def __getitem__(cls, name: str) -> "DiffusionAttentionBackendEnum":
def __getitem__(cls, name: str) -> "DiffusionAttentionBackendEnum": # type: ignore[override]
"""Get backend by name with helpful error messages."""
try:
return super().__getitem__(name) # type: ignore[return-value]
@@ -62,6 +62,7 @@ class DiffusionAttentionBackendEnum(Enum, metaclass=_DiffusionBackendEnumMeta):
SAGE_ATTN_3 = "vllm_omni.diffusion.attention.backends.sage_attn3.SageAttention3Backend"
CUDNN_ATTN = "vllm_omni.diffusion.attention.backends.cudnn_attn.CuDNNAttentionBackend"
FLASHINFER_ATTN = "vllm_omni.diffusion.attention.backends.flashinfer_attn.FlashInferAttentionBackend"
FASTVIDEO_VSA = "vllm_omni.diffusion.attention.backends.fastvideo_vsa.FastVideoVSABackend"
FLASH_ATTN_HUB = "vllm_omni.diffusion.attention.backends.flash_attn_hub.FlashAttentionHubBackend"
FLASH_ATTN_3_HUB = "vllm_omni.diffusion.attention.backends.flash_attn_hub.FlashAttention3HubBackend"
TRTLLM_ATTN = "vllm_omni.diffusion.attention.backends.trtllm_attn.TrtllmAttentionBackend"