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

[Other] Change all XPU to KunlunXin (#973)

Browse Source 
* [FlyCV] Bump up FlyCV -> official release 1.0.0

* XPU to KunlunXin

* update

* update model link

* update doc

* update device

* update code

* useless code

Co-authored-by: DefTruth <qiustudent_r@163.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
This commit is contained in:
yeliang2258
2022-12-27 10:02:02 +08:00
committed by GitHub
parent 6078bd9657
commit 45865c8724
111 changed files with 369 additions and 368 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
python/fastdeploy/runtime.py
View File

@@ -263,18 +263,18 @@ class RuntimeOption:
return
return self._option.use_gpu(device_id)
def use_xpu(self,
device_id=0,
l3_workspace_size=16 * 1024 * 1024,
locked=False,
autotune=True,
autotune_file="",
precision="int16",
adaptive_seqlen=False,
enable_multi_stream=False):
"""Inference with XPU
def use_kunlunxin(self,
device_id=0,
l3_workspace_size=16 * 1024 * 1024,
locked=False,
autotune=True,
autotune_file="",
precision="int16",
adaptive_seqlen=False,
enable_multi_stream=False):
"""Inference with KunlunXin XPU
:param device_id: (int)The index of XPU will be used for inference, default 0
:param device_id: (int)The index of KunlunXin XPU will be used for inference, default 0
:param l3_workspace_size: (int)The size of the video memory allocated by the l3 cache, the maximum is 16M, default 16M
:param locked: (bool)Whether the allocated L3 cache can be locked. If false, it means that the L3 cache is not locked,
and the allocated L3 cache can be shared by multiple models, and multiple models
@@ -285,11 +285,11 @@ class RuntimeOption:
the algorithm specified in the file will be used and autotune will not be performed again.
:param precision: (str)Calculation accuracy of multi_encoder
:param adaptive_seqlen: (bool)adaptive_seqlen Is the input of multi_encoder variable length
:param enable_multi_stream: (bool)Whether to enable the multi stream of xpu.
:param enable_multi_stream: (bool)Whether to enable the multi stream of KunlunXin XPU.
"""
return self._option.use_xpu(device_id, l3_workspace_size, locked,
autotune, autotune_file, precision,
adaptive_seqlen, enable_multi_stream)
return self._option.use_kunlunxin(device_id, l3_workspace_size, locked,
autotune, autotune_file, precision,
adaptive_seqlen, enable_multi_stream)
def use_cpu(self):
"""Inference with CPU