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

[XPU] support prefix cache (#4423)

Browse Source 
Co-authored-by: ddchenhao66 <dhaochen163.com>
This commit is contained in:
ddchenhao66
2025-10-16 11:27:41 +08:00
committed by GitHub
parent 5bde20b0c9
commit 8e392f0ea6
4 changed files with 112 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/engine/args_utils.py
View File

@@ -410,7 +410,7 @@ class EngineArgs:
self.enable_prefix_caching = False
if self.speculative_config is not None:
self.enable_prefix_caching = False
if not current_platform.is_cuda():
if not current_platform.is_cuda() and not current_platform.is_xpu():
self.enable_prefix_caching = False
# if self.dynamic_load_weight:
# self.enable_prefix_caching = False