anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[XPU] Update Bagel's flash_attn_varlen_func to fa utils (#1295)

Browse Source 
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
This commit is contained in:
liuzhenwei authored and GitHub committed 2026-02-12 21:33:06 +08:00
1 parent 36a79717c6
commit 00bd07b82b
2 files changed
+6 -1
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

vllm_omni/diffusion/models/bagel/bagel_transformer.py
+1 -1
View File
@@ -30,8 +30,8 @@ from vllm.model_executor.layers.linear import (
from vllm.model_executor.layers.vocab_parallel_embedding import VocabParallelEmbedding
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from vllm.transformers_utils.configs.bagel import BagelConfig
from vllm.vllm_flash_attn import flash_attn_varlen_func
from vllm_omni.diffusion.attention.backends.utils.fa import flash_attn_varlen_func
from vllm_omni.diffusion.layers.rope import RotaryEmbedding