init src 0.9.2

2026-01-09 15:09:53 +08:00
parent 0eb2c0a4b3
commit 41d98d4359
1438 changed files with 417605 additions and 683 deletions
--- a/vllm/init.py
+++ b/vllm/init.py
@@ -0,0 +1,96 @@
+# 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": ".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.executor.ray_utils import initialize_ray_cluster
+    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
+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",
+]