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] xpu currently disable prefix cache for VL model (#4695)

Browse Source 
Co-authored-by: ddchenhao66 <dhaochen163.com>
This commit is contained in:
ddchenhao66
2025-10-31 10:36:39 +08:00
committed by GitHub
parent b73a78155f
commit b87384aa70
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fastdeploy/engine/args_utils.py
View File

@@ -1078,6 +1078,10 @@ class EngineArgs:
all_dict = asdict(self)
model_cfg = ModelConfig(all_dict)
# XPU currently disable prefix cache for VL model
if current_platform.is_xpu() and (self.enable_mm or model_cfg.enable_mm):
self.enable_prefix_caching = False
if not model_cfg.is_unified_ckpt and hasattr(model_cfg, "tensor_parallel_size"):
self.tensor_parallel_size = model_cfg.tensor_parallel_size