indicate to mypy that InferenceProvider.batch_completion/batch_chat_completion is concrete

llama_stack/apis/inference/inference.py

@@ -1068,6 +1068,7 @@ class InferenceProvider(Protocol):
         :returns: A BatchCompletionResponse with the full completions.
         """
         raise NotImplementedError("Batch completion is not implemented")
+        return  # this is so mypy's safe-super rule will consider the method concrete
 
     @webmethod(route="/inference/chat-completion", method="POST")
     async def chat_completion(
@@ -1132,6 +1133,7 @@ class InferenceProvider(Protocol):
         :returns: A BatchChatCompletionResponse with the full completions.
         """
         raise NotImplementedError("Batch chat completion is not implemented")
+        return  # this is so mypy's safe-super rule will consider the method concrete
 
     @webmethod(route="/inference/embeddings", method="POST")
     async def embeddings(

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

@@ -9,7 +9,6 @@ from collections.abc import AsyncGenerator
 from llama_stack.apis.inference import (
     CompletionResponse,
     InferenceProvider,
-    InterleavedContent,
     LogProbConfig,
     Message,
     ResponseFormat,
@@ -100,25 +99,3 @@ class SentenceTransformersInferenceImpl(
         tool_config: ToolConfig | None = None,
     ) -> AsyncGenerator:
         raise ValueError("Sentence transformers don't support chat completion")
-
-    async def batch_completion(
-        self,
-        model_id: str,
-        content_batch: list[InterleavedContent],
-        sampling_params: SamplingParams | None = None,
-        response_format: ResponseFormat | None = None,
-        logprobs: LogProbConfig | None = None,
-    ):
-        raise NotImplementedError("Batch completion is not supported for Sentence Transformers")
-
-    async def batch_chat_completion(
-        self,
-        model_id: str,
-        messages_batch: list[list[Message]],
-        sampling_params: SamplingParams | None = None,
-        tools: list[ToolDefinition] | None = None,
-        tool_config: ToolConfig | None = None,
-        response_format: ResponseFormat | None = None,
-        logprobs: LogProbConfig | None = None,
-    ):
-        raise NotImplementedError("Batch chat completion is not supported for Sentence Transformers")

llama_stack/providers/remote/inference/ollama/ollama.py

@@ -619,28 +619,6 @@ class OllamaInferenceAdapter(
             response.id = id
             return response
 
-    async def batch_completion(
-        self,
-        model_id: str,
-        content_batch: list[InterleavedContent],
-        sampling_params: SamplingParams | None = None,
-        response_format: ResponseFormat | None = None,
-        logprobs: LogProbConfig | None = None,
-    ):
-        raise NotImplementedError("Batch completion is not supported for Ollama")
-
-    async def batch_chat_completion(
-        self,
-        model_id: str,
-        messages_batch: list[list[Message]],
-        sampling_params: SamplingParams | None = None,
-        tools: list[ToolDefinition] | None = None,
-        tool_config: ToolConfig | None = None,
-        response_format: ResponseFormat | None = None,
-        logprobs: LogProbConfig | None = None,
-    ):
-        raise NotImplementedError("Batch chat completion is not supported for Ollama")
-
 
 async def convert_message_to_openai_dict_for_ollama(message: Message) -> list[dict]:
     async def _convert_content(content) -> dict:

llama_stack/providers/remote/inference/vllm/vllm.py

@@ -711,25 +711,3 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
             user=user,
         )
         return await self.client.chat.completions.create(**params)  # type: ignore
-
-    async def batch_completion(
-        self,
-        model_id: str,
-        content_batch: list[InterleavedContent],
-        sampling_params: SamplingParams | None = None,
-        response_format: ResponseFormat | None = None,
-        logprobs: LogProbConfig | None = None,
-    ):
-        raise NotImplementedError("Batch completion is not supported for Ollama")
-
-    async def batch_chat_completion(
-        self,
-        model_id: str,
-        messages_batch: list[list[Message]],
-        sampling_params: SamplingParams | None = None,
-        tools: list[ToolDefinition] | None = None,
-        tool_config: ToolConfig | None = None,
-        response_format: ResponseFormat | None = None,
-        logprobs: LogProbConfig | None = None,
-    ):
-        raise NotImplementedError("Batch chat completion is not supported for vLLM")

llama_stack/providers/utils/inference/litellm_openai_mixin.py

@@ -429,28 +429,6 @@ class LiteLLMOpenAIMixin(
         )
         return await litellm.acompletion(**params)
 
-    async def batch_completion(
-        self,
-        model_id: str,
-        content_batch: list[InterleavedContent],
-        sampling_params: SamplingParams | None = None,
-        response_format: ResponseFormat | None = None,
-        logprobs: LogProbConfig | None = None,
-    ):
-        raise NotImplementedError("Batch completion is not supported for OpenAI Compat")
-
-    async def batch_chat_completion(
-        self,
-        model_id: str,
-        messages_batch: list[list[Message]],
-        sampling_params: SamplingParams | None = None,
-        tools: list[ToolDefinition] | None = None,
-        tool_config: ToolConfig | None = None,
-        response_format: ResponseFormat | None = None,
-        logprobs: LogProbConfig | None = None,
-    ):
-        raise NotImplementedError("Batch chat completion is not supported for OpenAI Compat")
-
     async def check_model_availability(self, model: str) -> bool:
         """
         Check if a specific model is available via LiteLLM for the current