Repository navigation
Expand file tree
/
Copy path__init__.py
More file actions
123 lines (121 loc) · 3.66 KB
/
Copy path__init__.py
File metadata and controls
123 lines (121 loc) · 3.66 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
from .attention import AttentionBackendTesterMixin, AttentionTesterMixin
from .cache import (
CacheTesterMixin,
FasterCacheConfigMixin,
FasterCacheTesterMixin,
FirstBlockCacheConfigMixin,
FirstBlockCacheTesterMixin,
MagCacheConfigMixin,
MagCacheTesterMixin,
PyramidAttentionBroadcastConfigMixin,
PyramidAttentionBroadcastTesterMixin,
SeaCacheConfigMixin,
SeaCacheTesterMixin,
TaylorSeerCacheConfigMixin,
TaylorSeerCacheTesterMixin,
)
from .common import BaseModelTesterConfig, ModelTesterMixin
from .compile import TorchCompileTesterMixin
from .ip_adapter import IPAdapterTesterMixin
from .lokr import LoKrTesterMixin
from .lora import LoraHotSwappingForModelTesterMixin, LoraTesterMixin
from .memory import CPUOffloadTesterMixin, GroupOffloadTesterMixin, LayerwiseCastingTesterMixin, MemoryTesterMixin
from .parallelism import (
ContextParallelAttentionBackendsTesterMixin,
ContextParallelTesterMixin,
TensorParallelNeuronTesterMixin,
TensorParallelTesterMixin,
TensorParallelTPUTesterMixin,
)
from .quantization import (
AutoRoundCompileTesterMixin,
AutoRoundConfigMixin,
AutoRoundTesterMixin,
BFLCompileTesterMixin,
BFLConfigMixin,
BFLTesterMixin,
BitsAndBytesCompileTesterMixin,
BitsAndBytesConfigMixin,
BitsAndBytesTesterMixin,
GGUFCompileTesterMixin,
GGUFConfigMixin,
GGUFTesterMixin,
ModelOptCompileTesterMixin,
ModelOptConfigMixin,
ModelOptTesterMixin,
NunchakuLiteCompileTesterMixin,
NunchakuLiteConfigMixin,
NunchakuLiteTesterMixin,
QuantizationCompileTesterMixin,
QuantizationTesterMixin,
SDNQCompileTesterMixin,
SDNQConfigMixin,
SDNQTesterMixin,
TorchAoCompileTesterMixin,
TorchAoConfigMixin,
TorchAoTesterMixin,
)
from .single_file import SingleFileTesterMixin
from .training import TrainingTesterMixin
from .utils import run_nondeterministic
__all__ = [
"AttentionBackendTesterMixin",
"AttentionTesterMixin",
"AutoRoundConfigMixin",
"AutoRoundTesterMixin",
"BFLCompileTesterMixin",
"BFLConfigMixin",
"BFLTesterMixin",
"BaseModelTesterConfig",
"BitsAndBytesCompileTesterMixin",
"BitsAndBytesConfigMixin",
"BitsAndBytesTesterMixin",
"CacheTesterMixin",
"ContextParallelTesterMixin",
"ContextParallelAttentionBackendsTesterMixin",
"TensorParallelTesterMixin",
"TensorParallelNeuronTesterMixin",
"TensorParallelTPUTesterMixin",
"CPUOffloadTesterMixin",
"FasterCacheConfigMixin",
"FasterCacheTesterMixin",
"FirstBlockCacheConfigMixin",
"FirstBlockCacheTesterMixin",
"MagCacheConfigMixin",
"MagCacheTesterMixin",
"GGUFCompileTesterMixin",
"GGUFConfigMixin",
"GGUFTesterMixin",
"GroupOffloadTesterMixin",
"IPAdapterTesterMixin",
"LayerwiseCastingTesterMixin",
"LoKrTesterMixin",
"LoraHotSwappingForModelTesterMixin",
"LoraTesterMixin",
"MemoryTesterMixin",
"ModelOptCompileTesterMixin",
"ModelOptConfigMixin",
"ModelOptTesterMixin",
"ModelTesterMixin",
"NunchakuLiteCompileTesterMixin",
"NunchakuLiteConfigMixin",
"NunchakuLiteTesterMixin",
"PyramidAttentionBroadcastConfigMixin",
"PyramidAttentionBroadcastTesterMixin",
"SeaCacheConfigMixin",
"SeaCacheTesterMixin",
"TaylorSeerCacheConfigMixin",
"TaylorSeerCacheTesterMixin",
"QuantizationCompileTesterMixin",
"QuantizationTesterMixin",
"run_nondeterministic",
"SDNQCompileTesterMixin",
"SDNQConfigMixin",
"SDNQTesterMixin",
"SingleFileTesterMixin",
"TorchAoCompileTesterMixin",
"TorchAoConfigMixin",
"TorchAoTesterMixin",
"TorchCompileTesterMixin",
"TrainingTesterMixin",
]