apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fix_fa3 (#4429)

Browse Source
This commit is contained in:
xiaoxiaohehe001
2025-10-15 16:19:39 +08:00
committed by GitHub
parent 9f1882d9a8
commit 6c15945e4d
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
fastdeploy/model_executor/layers/attention/flash_attn_backend.py
View File

@@ -125,6 +125,7 @@ class FlashAttentionBackend(AttentionBackend):
self.pd_disaggregation_mode: str = fd_config.parallel_config.pd_disaggregation_mode
self.start_layer_index: int = fd_config.model_config.start_layer_index
self.rope_3d: bool = getattr(fd_config.model_config, "rope_3d", False)
if fd_config.parallel_config.expert_parallel_rank is None:
fd_config.parallel_config.expert_parallel_rank = 0