Repository navigation
Expand file tree
/
Copy path__init__.py
More file actions
101 lines (92 loc) · 3.58 KB
/
Copy path__init__.py
File metadata and controls
101 lines (92 loc) · 3.58 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
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""vLLM: a high-throughput and memory-efficient inference engine for LLMs."""
# The version.py should be independent library, and we always import the
# version library first. Such assumption is critical for some customization.
from .version import __version__, __version_tuple__ # isort:skip
import typing
# The environment variables override should be imported before any other
# modules to ensure that the environment variables are set before any
# other modules are imported.
import vllm.env_override # noqa: F401
MODULE_ATTRS = {
"AsyncEngineArgs": ".engine.arg_utils:AsyncEngineArgs",
"EngineArgs": ".engine.arg_utils:EngineArgs",
"AsyncLLMEngine": ".engine.async_llm_engine:AsyncLLMEngine",
"LLMEngine": ".engine.llm_engine:LLMEngine",
"LLM": ".entrypoints.llm:LLM",
"initialize_ray_cluster": ".v1.executor.ray_utils:initialize_ray_cluster",
"PromptType": ".inputs:PromptType",
"TextPrompt": ".inputs:TextPrompt",
"TokensPrompt": ".inputs:TokensPrompt",
"ModelRegistry": ".model_executor.models:ModelRegistry",
"SamplingParams": ".sampling_params:SamplingParams",
"PoolingParams": ".pooling_params:PoolingParams",
"ClassificationOutput": ".outputs:ClassificationOutput",
"ClassificationRequestOutput": ".outputs:ClassificationRequestOutput",
"CompletionOutput": ".outputs:CompletionOutput",
"EmbeddingOutput": ".outputs:EmbeddingOutput",
"EmbeddingRequestOutput": ".outputs:EmbeddingRequestOutput",
"PoolingOutput": ".outputs:PoolingOutput",
"PoolingRequestOutput": ".outputs:PoolingRequestOutput",
"RequestOutput": ".outputs:RequestOutput",
"ScoringOutput": ".outputs:ScoringOutput",
"ScoringRequestOutput": ".outputs:ScoringRequestOutput",
}
if typing.TYPE_CHECKING:
from vllm.engine.arg_utils import AsyncEngineArgs, EngineArgs
from vllm.engine.async_llm_engine import AsyncLLMEngine
from vllm.engine.llm_engine import LLMEngine
from vllm.entrypoints.llm import LLM
from vllm.inputs import PromptType, TextPrompt, TokensPrompt
from vllm.model_executor.models import ModelRegistry
from vllm.outputs import (
ClassificationOutput,
ClassificationRequestOutput,
CompletionOutput,
EmbeddingOutput,
EmbeddingRequestOutput,
PoolingOutput,
PoolingRequestOutput,
RequestOutput,
ScoringOutput,
ScoringRequestOutput,
)
from vllm.pooling_params import PoolingParams
from vllm.sampling_params import SamplingParams
from vllm.v1.executor.ray_utils import initialize_ray_cluster
else:
def __getattr__(name: str) -> typing.Any:
from importlib import import_module
if name in MODULE_ATTRS:
module_name, attr_name = MODULE_ATTRS[name].split(":")
module = import_module(module_name, __package__)
return getattr(module, attr_name)
else:
raise AttributeError(f"module {__package__} has no attribute {name}")
__all__ = [
"__version__",
"__version_tuple__",
"LLM",
"ModelRegistry",
"PromptType",
"TextPrompt",
"TokensPrompt",
"SamplingParams",
"RequestOutput",
"CompletionOutput",
"PoolingOutput",
"PoolingRequestOutput",
"EmbeddingOutput",
"EmbeddingRequestOutput",
"ClassificationOutput",
"ClassificationRequestOutput",
"ScoringOutput",
"ScoringRequestOutput",
"LLMEngine",
"EngineArgs",
"AsyncLLMEngine",
"AsyncEngineArgs",
"initialize_ray_cluster",
"PoolingParams",
]