apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

dcu adapter ernie45t (#2756)

Browse Source 
Co-authored-by: lifu <lifu@sugon.com>
Co-authored-by: yongqiangma <xing.wo@163.com>
This commit is contained in:
lifulll
2025-07-09 18:56:27 +08:00
committed by GitHub
parent 03a74995b8
commit 1f28bdf994
30 changed files with 1133 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/model_executor/layers/attention/mla_attention_backend.py
View File

@@ -29,7 +29,7 @@ from fastdeploy.model_executor.layers.attention.ops import (
open_shm_and_get_meta_signal)
from fastdeploy.platforms import current_platform
if current_platform.is_cuda():
if current_platform.is_cuda() and not current_platform.is_dcu():
from fastdeploy.model_executor.ops.gpu import (decode_mla_write_cache,
multi_head_latent_attention,
prefill_mla_write_cache)