Inline vLLM inference provider (#181)

This is just like `local` using `meta-reference` for everything except
it uses `vllm` for inference.

Docker works, but So far, `conda` is a bit easier to use with the vllm
provider. The default container base image does not include all the
necessary libraries for all vllm features. More cuda dependencies are
necessary.

I started changing this base image used in this template, but it also
required changes to the Dockerfile, so it was getting too involved to
include in the first PR.

Working so far:

* `python -m llama_stack.apis.inference.client localhost 5000 --model Llama3.2-1B-Instruct --stream True`
* `python -m llama_stack.apis.inference.client localhost 5000 --model Llama3.2-1B-Instruct --stream False`

Example:

```
$ python -m llama_stack.apis.inference.client localhost 5000 --model Llama3.2-1B-Instruct --stream False
User>hello world, write me a 2 sentence poem about the moon
Assistant>
The moon glows bright in the midnight sky
A beacon of light,
```

I have only tested these models:

* `Llama3.1-8B-Instruct` - across 4 GPUs (tensor_parallel_size = 4)
* `Llama3.2-1B-Instruct` - on a single GPU (tensor_parallel_size = 1)

llama_stack/providers/registry/inference.py

@@ -104,4 +104,13 @@ def available_providers() -> List[ProviderSpec]:
                 config_class="llama_stack.providers.adapters.inference.bedrock.BedrockConfig",
             ),
         ),
+        InlineProviderSpec(
+            api=Api.inference,
+            provider_type="vllm",
+            pip_packages=[
+                "vllm",
+            ],
+            module="llama_stack.providers.impls.vllm",
+            config_class="llama_stack.providers.impls.vllm.VLLMConfig",
+        ),
     ]