[Deprecation] Remove inputs arg fallback in Engine classes (#18799)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

vllm/engine/llm_engine.py

@@ -11,10 +11,10 @@ from functools import partial
 from typing import (TYPE_CHECKING, Any, Callable, ClassVar, Deque, Dict,
                     Iterable, List, Literal, Mapping, NamedTuple, Optional)
 from typing import Sequence as GenericSequence
-from typing import Set, Type, Union, cast, overload
+from typing import Set, Type, Union, cast
 
 import torch
-from typing_extensions import TypeVar, deprecated
+from typing_extensions import TypeVar
 
 import vllm.envs as envs
 from vllm.config import (DecodingConfig, LoRAConfig, ModelConfig,
@@ -58,8 +58,7 @@ from vllm.transformers_utils.tokenizer_group import (
     TokenizerGroup, init_tokenizer_from_configs)
 from vllm.usage.usage_lib import (UsageContext, is_usage_stats_enabled,
                                   usage_message)
-from vllm.utils import (Counter, Device, deprecate_kwargs,
-                        resolve_obj_by_qualname, weak_bind)
+from vllm.utils import Counter, Device, resolve_obj_by_qualname, weak_bind
 from vllm.version import __version__ as VLLM_VERSION
 from vllm.worker.model_runner_base import InputProcessingError
 
@@ -629,7 +628,6 @@ class LLMEngine:
     def stop_remote_worker_execution_loop(self) -> None:
         self.model_executor.stop_remote_worker_execution_loop()
 
-    @overload
     def add_request(
         self,
         request_id: str,
@@ -641,42 +639,6 @@ class LLMEngine:
         trace_headers: Optional[Mapping[str, str]] = None,
         prompt_adapter_request: Optional[PromptAdapterRequest] = None,
         priority: int = 0,
-    ) -> None:
-        ...
-
-    @overload
-    @deprecated("'inputs' will be renamed to 'prompt")
-    def add_request(
-        self,
-        request_id: str,
-        *,
-        inputs: PromptType,
-        params: Union[SamplingParams, PoolingParams],
-        arrival_time: Optional[float] = None,
-        lora_request: Optional[LoRARequest] = None,
-        trace_headers: Optional[Mapping[str, str]] = None,
-        prompt_adapter_request: Optional[PromptAdapterRequest] = None,
-        priority: int = 0,
-    ) -> None:
-        ...
-
-    @deprecate_kwargs(
-        "inputs",
-        additional_message="Please use the 'prompt' parameter instead.",
-    )
-    def add_request(
-            self,
-            request_id: str,
-            prompt: Optional[PromptType] = None,
-            params: Optional[Union[SamplingParams, PoolingParams]] = None,
-            arrival_time: Optional[float] = None,
-            lora_request: Optional[LoRARequest] = None,
-            tokenization_kwargs: Optional[dict[str, Any]] = None,
-            trace_headers: Optional[Mapping[str, str]] = None,
-            prompt_adapter_request: Optional[PromptAdapterRequest] = None,
-            priority: int = 0,
-            *,
-            inputs: Optional[PromptType] = None,  # DEPRECATED
     ) -> None:
         """Add a request to the engine's request pool.
 
@@ -725,10 +687,6 @@ class LLMEngine:
             >>> # continue the request processing
             >>> ...
         """
-        if inputs is not None:
-            prompt = inputs
-        assert prompt is not None and params is not None
-
         if lora_request is not None and not self.lora_config:
             raise ValueError(f"Got lora_request {lora_request} but LoRA is "
                              "not enabled!")