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

polish code with new pre-commit rule (#2923)

Browse Source
This commit is contained in:
Zero Rains
2025-07-19 23:19:27 +08:00
committed by GitHub
parent b8676d71a8
commit 25698d56d1
424 changed files with 14307 additions and 13518 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
fastdeploy/platforms/cuda.py
View File

@@ -25,6 +25,7 @@ class CUDAPlatform(Platform):
"""
cuda platform class
"""
device_name = "gpu"
@classmethod
@@ -39,7 +40,8 @@ class CUDAPlatform(Platform):
logger.warning(
"You are using GPU version PaddlePaddle, but there is no GPU "
"detected on your machine. Maybe CUDA devices is not set properly."
f"\n Original Error is {e}")
f"\n Original Error is {e}"
)
return False
@classmethod
@@ -49,24 +51,16 @@ class CUDAPlatform(Platform):
"""
if selected_backend == _Backend.NATIVE_ATTN:
logger.info("Using NATIVE ATTN backend.")
return (
"fastdeploy.model_executor.layers.attention.PaddleNativeAttnBackend"
)
return "fastdeploy.model_executor.layers.attention.PaddleNativeAttnBackend"
elif selected_backend == _Backend.APPEND_ATTN:
logger.info("Using APPEND ATTN backend.")
return (
"fastdeploy.model_executor.layers.attention.AppendAttentionBackend"
)
return "fastdeploy.model_executor.layers.attention.AppendAttentionBackend"
elif selected_backend == _Backend.MLA_ATTN:
logger.info("Using MLA ATTN backend.")
return (
"fastdeploy.model_executor.layers.attention.MLAAttentionBackend"
)
return "fastdeploy.model_executor.layers.attention.MLAAttentionBackend"
elif selected_backend == _Backend.FLASH_ATTN:
logger.info("Using FLASH ATTN backend.")
return (
"fastdeploy.model_executor.layers.attention.FlashAttentionBackend"
)
return "fastdeploy.model_executor.layers.attention.FlashAttentionBackend"
else:
raise ValueError(
"Invalid attention backend you specified.\n"