chore: remove /v1/inference/completion and implementations (#3622)

# What does this PR do?

the /inference/completion route is gone. this removes the
implementations.

## Test Plan

ci

llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py

@@ -5,9 +5,9 @@
 # the root directory of this source tree.
 
 from collections.abc import AsyncGenerator
+from typing import Any
 
 from llama_stack.apis.inference import (
-    CompletionResponse,
     InferenceProvider,
     LogProbConfig,
     Message,
@@ -18,6 +18,7 @@ from llama_stack.apis.inference import (
     ToolDefinition,
     ToolPromptFormat,
 )
+from llama_stack.apis.inference.inference import OpenAICompletion
 from llama_stack.apis.models import ModelType
 from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
@@ -26,7 +27,6 @@ from llama_stack.providers.utils.inference.embedding_mixin import (
 )
 from llama_stack.providers.utils.inference.openai_compat import (
     OpenAIChatCompletionToLlamaStackMixin,
-    OpenAICompletionToLlamaStackMixin,
 )
 
 from .config import SentenceTransformersInferenceConfig
@@ -36,7 +36,6 @@ log = get_logger(name=__name__, category="inference")
 
 class SentenceTransformersInferenceImpl(
     OpenAIChatCompletionToLlamaStackMixin,
-    OpenAICompletionToLlamaStackMixin,
     SentenceTransformerEmbeddingMixin,
     InferenceProvider,
     ModelsProtocolPrivate,
@@ -74,17 +73,6 @@ class SentenceTransformersInferenceImpl(
     async def unregister_model(self, model_id: str) -> None:
         pass
 
-    async def completion(
-        self,
-        model_id: str,
-        content: str,
-        sampling_params: SamplingParams | None = None,
-        response_format: ResponseFormat | None = None,
-        stream: bool | None = False,
-        logprobs: LogProbConfig | None = None,
-    ) -> CompletionResponse | AsyncGenerator:
-        raise ValueError("Sentence transformers don't support completion")
-
     async def chat_completion(
         self,
         model_id: str,
@@ -99,3 +87,31 @@ class SentenceTransformersInferenceImpl(
         tool_config: ToolConfig | None = None,
     ) -> AsyncGenerator:
         raise ValueError("Sentence transformers don't support chat completion")
+
+    async def openai_completion(
+        self,
+        # Standard OpenAI completion parameters
+        model: str,
+        prompt: str | list[str] | list[int] | list[list[int]],
+        best_of: int | None = None,
+        echo: bool | None = None,
+        frequency_penalty: float | None = None,
+        logit_bias: dict[str, float] | None = None,
+        logprobs: bool | None = None,
+        max_tokens: int | None = None,
+        n: int | None = None,
+        presence_penalty: float | None = None,
+        seed: int | None = None,
+        stop: str | list[str] | None = None,
+        stream: bool | None = None,
+        stream_options: dict[str, Any] | None = None,
+        temperature: float | None = None,
+        top_p: float | None = None,
+        user: str | None = None,
+        # vLLM-specific parameters
+        guided_choice: list[str] | None = None,
+        prompt_logprobs: int | None = None,
+        # for fill-in-the-middle type completion
+        suffix: str | None = None,
+    ) -> OpenAICompletion:
+        raise NotImplementedError("OpenAI completion not supported by sentence transformers provider")