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

[Metax] support ENABLE_V1_KVCACHE_SCHEDULER (#5163)

Browse Source
This commit is contained in:
xiaozude
2025-11-24 19:19:49 +08:00
committed by GitHub
parent e150a418d4
commit d5bd64336a
5 changed files with 24 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/engine/args_utils.py
View File

@@ -523,7 +523,7 @@ class EngineArgs:
f"= {expected_ports}, but got {len(self.rdma_comm_ports)}."
)
if not current_platform.is_cuda() and not current_platform.is_xpu():
if not (current_platform.is_cuda() or current_platform.is_xpu() or current_platform.is_maca()):
envs.ENABLE_V1_KVCACHE_SCHEDULER = 0
if self.guided_decoding_backend != "off":
envs.ENABLE_V1_KVCACHE_SCHEDULER = 0