chore: kill inline::vllm (#2824)

Inline _inference_ providers haven't proved to be very useful -- they
are rarely used. And for good reason -- it is almost never a good idea
to include a complex (distributed) inference engine bundled into a
distributed stateful front-end server serving many other things.
Responsibility should be split properly.

See Discord discussion:
1395849853

llama_stack/templates/vllm-gpu/build.yaml

@@ -1,35 +0,0 @@
-version: 2
-distribution_spec:
-  description: Use a built-in vLLM engine for running LLM inference
-  providers:
-    inference:
-    - inline::vllm
-    - inline::sentence-transformers
-    vector_io:
-    - inline::faiss
-    - remote::chromadb
-    - remote::pgvector
-    safety:
-    - inline::llama-guard
-    agents:
-    - inline::meta-reference
-    telemetry:
-    - inline::meta-reference
-    eval:
-    - inline::meta-reference
-    datasetio:
-    - remote::huggingface
-    - inline::localfs
-    scoring:
-    - inline::basic
-    - inline::llm-as-judge
-    - inline::braintrust
-    tool_runtime:
-    - remote::brave-search
-    - remote::tavily-search
-    - inline::rag-runtime
-    - remote::model-context-protocol
-image_type: conda
-additional_pip_packages:
-- aiosqlite
-- sqlalchemy[asyncio]