| 1 | # SPDX-License-Identifier: Apache-2.0 |
| 2 | # SPDX-FileCopyrightText: Copyright contributors to the vLLM project |
| 3 | from typing import TYPE_CHECKING |
| 4 | |
| 5 | from vllm.config import ModelConfig |
| 6 | from vllm.tasks import SupportedTask |
| 7 | |
| 8 | if TYPE_CHECKING: |
| 9 | from vllm.entrypoints.serve.sagemaker.api_router import ( |
| 10 | EndpointFn, |
| 11 | GetHandlerFn, |
| 12 | RequestType, |
| 13 | ) |
| 14 | |
| 15 | |
| 16 | def get_generate_invocation_types( |
| 17 | supported_tasks: tuple["SupportedTask", ...], |
| 18 | model_config: ModelConfig | None = None, |
| 19 | ): |
| 20 | # NOTE: Items defined earlier take higher priority |
| 21 | invocation_types: list[tuple[RequestType, tuple[GetHandlerFn, EndpointFn]]] = [] |
| 22 | |
| 23 | if "generate" in supported_tasks: |
| 24 | from vllm.entrypoints.openai.chat_completion.api_router import ( |
| 25 | chat, |
| 26 | create_chat_completion, |
| 27 | ) |
| 28 | from vllm.entrypoints.openai.chat_completion.protocol import ( |
| 29 | ChatCompletionRequest, |
| 30 | ) |
| 31 | from vllm.entrypoints.openai.completion.api_router import ( |
| 32 | completion, |
| 33 | create_completion, |
| 34 | ) |
| 35 | from vllm.entrypoints.openai.completion.protocol import CompletionRequest |
| 36 | |
| 37 | invocation_types += [ |
| 38 | (ChatCompletionRequest, (chat, create_chat_completion)), |
| 39 | (CompletionRequest, (completion, create_completion)), |
| 40 | ] |
| 41 | |
| 42 | return invocation_types |