imb 1.0.2__py3-none-any.whl → 1.0.3__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
imb/triton.py CHANGED
@@ -25,8 +25,6 @@ class TritonClient(BaseClient):
25
25
  model_name: str,
26
26
  max_batch_size: int = 0,
27
27
  sample_inputs: Optional[List[np.ndarray]] = None,
28
- timeout: int = 10,
29
- resend_count: int = 10,
30
28
  fixed_batch: bool = True,
31
29
  is_async: bool = False,
32
30
  use_cuda_shm: bool = False,
@@ -43,8 +41,6 @@ class TritonClient(BaseClient):
43
41
  model_name (str): name of the model endpoint
44
42
  max_batch_size (int, optional): max batch size. Defaults to 0 (get value from triton config).
45
43
  sample_inputs (Optional[List[np.ndarray]], optional): samples for warmup. Defaults to None (zeros array).
46
- timeout (int, optional): triton client timeout. Defaults to 10.
47
- resend_count (int, optional): triton client resend count. Defaults to 10.
48
44
  fixed_batch (bool, optional): use fixed batch size, using padding for smaller batch. Defaults to True.
49
45
  is_async (bool, optional): async inference. Defaults to False.
50
46
  use_cuda_shm (bool, optional): use cuda shared memory. Defaults to False.
@@ -63,8 +59,6 @@ class TritonClient(BaseClient):
63
59
  self.is_async = is_async
64
60
  self.use_cuda_shm = use_cuda_shm
65
61
  self.use_system_shm = use_system_shm
66
- self.triton_timeout = timeout
67
- self.resend_count = resend_count
68
62
  self.max_shm_regions = max_shm_regions
69
63
  self.return_dict = return_dict
70
64
 
@@ -130,9 +124,7 @@ class TritonClient(BaseClient):
130
124
  self.triton_client = self.client_module.InferenceServerClient(
131
125
  url=self.url,
132
126
  verbose=False,
133
- ssl=False,
134
- network_timeout=self.triton_timeout,
135
- connection_timeout=self.triton_timeout
127
+ ssl=False
136
128
  )
137
129
 
138
130
  def _load_model_params(self, user_max_batch_size: int) -> None:
@@ -1,10 +1,12 @@
1
- Metadata-Version: 2.2
1
+ Metadata-Version: 2.1
2
2
  Name: imb
3
- Version: 1.0.2
3
+ Version: 1.0.3
4
4
  Summary: Python library for run inference of deep learning models in different backends
5
5
  Home-page: https://github.com/TheConstant3/InferenceMultiBackend
6
6
  Author: p-constant
7
7
  Author-email: nikshorop@gmail.com
8
+ License: UNKNOWN
9
+ Platform: UNKNOWN
8
10
  Classifier: Programming Language :: Python :: 3.8
9
11
  Classifier: License :: OSI Approved :: MIT License
10
12
  Classifier: Operating System :: OS Independent
@@ -12,26 +14,16 @@ Requires-Python: >=3.8
12
14
  Description-Content-Type: text/markdown
13
15
  License-File: LICENSE
14
16
  Requires-Dist: numpy
15
- Provides-Extra: triton
16
- Requires-Dist: tritonclient[all]>=2.38.0; extra == "triton"
17
- Provides-Extra: onnxcpu
18
- Requires-Dist: onnxruntime>=1.16.0; extra == "onnxcpu"
19
- Provides-Extra: onnxgpu
20
- Requires-Dist: onnxruntime-gpu>=1.16.0; extra == "onnxgpu"
21
17
  Provides-Extra: all
22
18
  Requires-Dist: tritonclient[all]>=2.38.0; extra == "all"
23
19
  Requires-Dist: onnxruntime>=1.16.0; extra == "all"
24
20
  Requires-Dist: onnxruntime-gpu>=1.16.0; extra == "all"
25
- Dynamic: author
26
- Dynamic: author-email
27
- Dynamic: classifier
28
- Dynamic: description
29
- Dynamic: description-content-type
30
- Dynamic: home-page
31
- Dynamic: provides-extra
32
- Dynamic: requires-dist
33
- Dynamic: requires-python
34
- Dynamic: summary
21
+ Provides-Extra: onnxcpu
22
+ Requires-Dist: onnxruntime>=1.16.0; extra == "onnxcpu"
23
+ Provides-Extra: onnxgpu
24
+ Requires-Dist: onnxruntime-gpu>=1.16.0; extra == "onnxgpu"
25
+ Provides-Extra: triton
26
+ Requires-Dist: tritonclient[all]>=2.38.0; extra == "triton"
35
27
 
36
28
  # InferenceMultiBackend
37
29
 
@@ -111,3 +103,4 @@ fixed_batch - if fixed batch is True, then each batch will have fixed size (padd
111
103
  warmup - if True, model will run several calls on sample_inputs while initialization.
112
104
 
113
105
  return_dict - if True, __call__ return dict {'output_name1': output_value1, ...}, else [output_value1, ...]
106
+
@@ -0,0 +1,9 @@
1
+ imb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
2
+ imb/base.py,sha256=oBmiTu4rHgzED5kCxKPvS9e3PhI229Pj5lxuPm7ep6M,5189
3
+ imb/onnx.py,sha256=g3vQBJPeln0YUOQ1X9RjZce8AAi-7SXntLyevOZZdG8,4100
4
+ imb/triton.py,sha256=_mOnt9msTOhxsQIKGgsKFXFmFofNKiwAVS1uJaW0PWA,21337
5
+ imb-1.0.3.dist-info/LICENSE,sha256=pAZXnNE2dxxwXFIduGyn1gpvPefJtUYOYZOi3yeGG94,1068
6
+ imb-1.0.3.dist-info/METADATA,sha256=r7uFjfpNAeQ1GoPZgscZbUKaMzlmsywMd00eroOz9Qc,3129
7
+ imb-1.0.3.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
8
+ imb-1.0.3.dist-info/top_level.txt,sha256=kY8Fp1i_MzTZhuoVhVexG762D8HBd-THfX_lfw4EZmY,4
9
+ imb-1.0.3.dist-info/RECORD,,
@@ -1,5 +1,5 @@
1
1
  Wheel-Version: 1.0
2
- Generator: setuptools (75.8.0)
2
+ Generator: bdist_wheel (0.44.0)
3
3
  Root-Is-Purelib: true
4
4
  Tag: py3-none-any
5
5
 
@@ -1,9 +0,0 @@
1
- imb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
2
- imb/base.py,sha256=oBmiTu4rHgzED5kCxKPvS9e3PhI229Pj5lxuPm7ep6M,5189
3
- imb/onnx.py,sha256=g3vQBJPeln0YUOQ1X9RjZce8AAi-7SXntLyevOZZdG8,4100
4
- imb/triton.py,sha256=92d3tvCniWGSnC1UyjkQ5OcXgSbsBnX6T2hoewLal0k,21796
5
- imb-1.0.2.dist-info/LICENSE,sha256=pAZXnNE2dxxwXFIduGyn1gpvPefJtUYOYZOi3yeGG94,1068
6
- imb-1.0.2.dist-info/METADATA,sha256=lEzhVDdcdNHZeECQPisnQcZDjueOFP8zuhVTDh4Vi3s,3314
7
- imb-1.0.2.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
8
- imb-1.0.2.dist-info/top_level.txt,sha256=kY8Fp1i_MzTZhuoVhVexG762D8HBd-THfX_lfw4EZmY,4
9
- imb-1.0.2.dist-info/RECORD,,
File without changes