chore(api): remove batch inference (#3261)

# What does this PR do?

APIs removed:
 - POST /v1/batch-inference/completion
 - POST /v1/batch-inference/chat-completion
 - POST /v1/inference/batch-completion
 - POST /v1/inference/batch-chat-completion

note -
- batch-completion & batch-chat-completion were only implemented for
inference=inline::meta-reference
 - batch-inference were not implemented

llama_stack/core/routers/inference.py

@@ -20,8 +20,6 @@ from llama_stack.apis.common.content_types import (
 )
 from llama_stack.apis.common.errors import ModelNotFoundError, ModelTypeError
 from llama_stack.apis.inference import (
-    BatchChatCompletionResponse,
-    BatchCompletionResponse,
     ChatCompletionResponse,
     ChatCompletionResponseEventType,
     ChatCompletionResponseStreamChunk,
@@ -273,30 +271,6 @@ class InferenceRouter(Inference):
         )
         return response
 
-    async def batch_chat_completion(
-        self,
-        model_id: str,
-        messages_batch: list[list[Message]],
-        tools: list[ToolDefinition] | None = None,
-        tool_config: ToolConfig | None = None,
-        sampling_params: SamplingParams | None = None,
-        response_format: ResponseFormat | None = None,
-        logprobs: LogProbConfig | None = None,
-    ) -> BatchChatCompletionResponse:
-        logger.debug(
-            f"InferenceRouter.batch_chat_completion: {model_id=}, {len(messages_batch)=}, {sampling_params=}, {response_format=}, {logprobs=}",
-        )
-        provider = await self.routing_table.get_provider_impl(model_id)
-        return await provider.batch_chat_completion(
-            model_id=model_id,
-            messages_batch=messages_batch,
-            tools=tools,
-            tool_config=tool_config,
-            sampling_params=sampling_params,
-            response_format=response_format,
-            logprobs=logprobs,
-        )
-
     async def completion(
         self,
         model_id: str,
@@ -338,20 +312,6 @@ class InferenceRouter(Inference):
 
         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,
-    ) -> BatchCompletionResponse:
-        logger.debug(
-            f"InferenceRouter.batch_completion: {model_id=}, {len(content_batch)=}, {sampling_params=}, {response_format=}, {logprobs=}",
-        )
-        provider = await self.routing_table.get_provider_impl(model_id)
-        return await provider.batch_completion(model_id, content_batch, sampling_params, response_format, logprobs)
-
     async def embeddings(
         self,
         model_id: str,

llama_stack/core/stack.py

@@ -14,7 +14,6 @@ from typing import Any
 import yaml
 
 from llama_stack.apis.agents import Agents
-from llama_stack.apis.batch_inference import BatchInference
 from llama_stack.apis.benchmarks import Benchmarks
 from llama_stack.apis.datasetio import DatasetIO
 from llama_stack.apis.datasets import Datasets
@@ -54,7 +53,6 @@ class LlamaStack(
     Providers,
     VectorDBs,
     Inference,
-    BatchInference,
     Agents,
     Safety,
     SyntheticDataGeneration,