Add OpenAI-Compatible models, completions, chat/completions endpoints

This stubs in some OpenAI server-side compatibility with three new
endpoints:

/v1/openai/v1/models
/v1/openai/v1/completions
/v1/openai/v1/chat/completions

This gives common inference apps using OpenAI clients the ability to
talk to Llama Stack using an endpoint like
http://localhost:8321/v1/openai/v1 .

The two "v1" instances in there isn't awesome, but the thinking is
that Llama Stack's API is v1 and then our OpenAI compatibility layer
is compatible with OpenAI V1. And, some OpenAI clients implicitly
assume the URL ends with "v1", so this gives maximum compatibility.

The openai models endpoint is implemented in the routing layer, and
just returns all the models Llama Stack knows about.

The chat endpoints are only actually implemented for the remote-vllm
provider right now, and it just proxies the completion and chat
completion requests to the backend vLLM.

The goal to support this for every inference provider - proxying
directly to the provider's OpenAI endpoint for OpenAI-compatible
providers. For providers that don't have an OpenAI-compatible API,
we'll add a mixin to translate incoming OpenAI requests to Llama Stack
inference requests and translate the Llama Stack inference responses
to OpenAI responses.

llama_stack/distribution/routers/routers.py

@@ -7,6 +7,10 @@
 import time
 from typing import Any, AsyncGenerator, AsyncIterator, Dict, List, Optional, Union
 
+from openai.types.chat import ChatCompletion as OpenAIChatCompletion
+from openai.types.chat import ChatCompletionMessageParam as OpenAIChatCompletionMessageParam
+from openai.types.completion import Completion as OpenAICompletion
+
 from llama_stack.apis.common.content_types import (
     URL,
     InterleavedContent,
@@ -419,6 +423,122 @@ class InferenceRouter(Inference):
             task_type=task_type,
         )
 
+    async def openai_completion(
+        self,
+        model: str,
+        prompt: str,
+        best_of: Optional[int] = None,
+        echo: Optional[bool] = None,
+        frequency_penalty: Optional[float] = None,
+        logit_bias: Optional[Dict[str, float]] = None,
+        logprobs: Optional[bool] = None,
+        max_tokens: Optional[int] = None,
+        n: Optional[int] = None,
+        presence_penalty: Optional[float] = None,
+        seed: Optional[int] = None,
+        stop: Optional[Union[str, List[str]]] = None,
+        stream: Optional[bool] = None,
+        stream_options: Optional[Dict[str, Any]] = None,
+        temperature: Optional[float] = None,
+        top_p: Optional[float] = None,
+        user: Optional[str] = None,
+    ) -> OpenAICompletion:
+        logger.debug(
+            f"InferenceRouter.openai_completion: {model=}, {stream=}, {prompt=}",
+        )
+        model_obj = await self.routing_table.get_model(model)
+        if model_obj is None:
+            raise ValueError(f"Model '{model}' not found")
+        if model_obj.model_type == ModelType.embedding:
+            raise ValueError(f"Model '{model}' is an embedding model and does not support completions")
+
+        params = dict(
+            model=model_obj.identifier,
+            prompt=prompt,
+            best_of=best_of,
+            echo=echo,
+            frequency_penalty=frequency_penalty,
+            logit_bias=logit_bias,
+            logprobs=logprobs,
+            max_tokens=max_tokens,
+            n=n,
+            presence_penalty=presence_penalty,
+            seed=seed,
+            stop=stop,
+            stream=stream,
+            stream_options=stream_options,
+            temperature=temperature,
+            top_p=top_p,
+            user=user,
+        )
+
+        provider = self.routing_table.get_provider_impl(model_obj.identifier)
+        return await provider.openai_completion(**params)
+
+    async def openai_chat_completion(
+        self,
+        model: str,
+        messages: List[OpenAIChatCompletionMessageParam],
+        frequency_penalty: Optional[float] = None,
+        function_call: Optional[Union[str, Dict[str, Any]]] = None,
+        functions: Optional[List[Dict[str, Any]]] = None,
+        logit_bias: Optional[Dict[str, float]] = None,
+        logprobs: Optional[bool] = None,
+        max_completion_tokens: Optional[int] = None,
+        max_tokens: Optional[int] = None,
+        n: Optional[int] = None,
+        parallel_tool_calls: Optional[bool] = None,
+        presence_penalty: Optional[float] = None,
+        response_format: Optional[Dict[str, str]] = None,
+        seed: Optional[int] = None,
+        stop: Optional[Union[str, List[str]]] = None,
+        stream: Optional[bool] = None,
+        stream_options: Optional[Dict[str, Any]] = None,
+        temperature: Optional[float] = None,
+        tool_choice: Optional[Union[str, Dict[str, Any]]] = None,
+        tools: Optional[List[Dict[str, Any]]] = None,
+        top_logprobs: Optional[int] = None,
+        top_p: Optional[float] = None,
+        user: Optional[str] = None,
+    ) -> OpenAIChatCompletion:
+        logger.debug(
+            f"InferenceRouter.openai_chat_completion: {model=}, {stream=}, {messages=}",
+        )
+        model_obj = await self.routing_table.get_model(model)
+        if model_obj is None:
+            raise ValueError(f"Model '{model}' not found")
+        if model_obj.model_type == ModelType.embedding:
+            raise ValueError(f"Model '{model}' is an embedding model and does not support chat completions")
+
+        params = dict(
+            model=model_obj.identifier,
+            messages=messages,
+            frequency_penalty=frequency_penalty,
+            function_call=function_call,
+            functions=functions,
+            logit_bias=logit_bias,
+            logprobs=logprobs,
+            max_completion_tokens=max_completion_tokens,
+            max_tokens=max_tokens,
+            n=n,
+            parallel_tool_calls=parallel_tool_calls,
+            presence_penalty=presence_penalty,
+            response_format=response_format,
+            seed=seed,
+            stop=stop,
+            stream=stream,
+            stream_options=stream_options,
+            temperature=temperature,
+            tool_choice=tool_choice,
+            tools=tools,
+            top_logprobs=top_logprobs,
+            top_p=top_p,
+            user=user,
+        )
+
+        provider = self.routing_table.get_provider_impl(model_obj.identifier)
+        return await provider.openai_chat_completion(**params)
+
 
 class SafetyRouter(Safety):
     def __init__(