feat: add batch inference API to llama stack inference (#1945)

# What does this PR do?

This PR adds two methods to the Inference API:
- `batch_completion`
- `batch_chat_completion`

The motivation is for evaluations targeting a local inference engine
(like meta-reference or vllm) where batch APIs provide for a substantial
amount of acceleration.

Why did I not add this to `Api.batch_inference` though? That just
resulted in a _lot_ more book-keeping given the structure of Llama
Stack. Had I done that, I would have needed to create a notion of a
"batch model" resource, setup routing based on that, etc. This does not
sound ideal.

So what's the future of the batch inference API? I am not sure. Maybe we
can keep it for true _asynchronous_ execution. So you can submit
requests, and it can return a Job instance, etc.

## Test Plan

Run meta-reference-gpu using:
```bash
export INFERENCE_MODEL=meta-llama/Llama-4-Scout-17B-16E-Instruct
export INFERENCE_CHECKPOINT_DIR=../checkpoints/Llama-4-Scout-17B-16E-Instruct-20250331210000
export MODEL_PARALLEL_SIZE=4
export MAX_BATCH_SIZE=32
export MAX_SEQ_LEN=6144

LLAMA_MODELS_DEBUG=1 llama stack run meta-reference-gpu
```

Then run the batch inference test case.

llama_stack/providers/inline/inference/meta_reference/config.py

@@ -52,14 +52,17 @@ class MetaReferenceInferenceConfig(BaseModel):
         checkpoint_dir: str = "${env.CHECKPOINT_DIR:null}",
         quantization_type: str = "${env.QUANTIZATION_TYPE:bf16}",
         model_parallel_size: str = "${env.MODEL_PARALLEL_SIZE:0}",
+        max_batch_size: str = "${env.MAX_BATCH_SIZE:1}",
+        max_seq_len: str = "${env.MAX_SEQ_LEN:4096}",
         **kwargs,
     ) -> Dict[str, Any]:
         return {
             "model": model,
-            "max_seq_len": 4096,
             "checkpoint_dir": checkpoint_dir,
             "quantization": {
                 "type": quantization_type,
             },
             "model_parallel_size": model_parallel_size,
+            "max_batch_size": max_batch_size,
+            "max_seq_len": max_seq_len,
         }