Upload vllm_plugin/README.md with huggingface_hub

vllm_plugin/README.md

@@ -0,0 +1,43 @@
+# vLLM Plugin for Borealis
+
+vLLM plugin to enable inference with Borealis Audio-Language Model.
+
+## Installation
+
+```bash
+pip install -e .
+```
+
+## Usage
+
+After installation, the Borealis model will be automatically registered with vLLM.
+
+```python
+from vllm import LLM, SamplingParams
+
+# Load model
+llm = LLM(
+    model="Vikhrmodels/Borealis-5b-it",
+    trust_remote_code=True,
+)
+
+# Inference with audio
+# Note: Audio preprocessing should be done separately
+sampling_params = SamplingParams(temperature=0.7, max_tokens=256)
+outputs = llm.generate(prompts, sampling_params)
+```
+
+## Architecture
+
+Borealis combines:
+- **Whisper Large V3** encoder for audio processing
+- **Qwen3-4B** LLM for text generation
+- **Adapter** to project audio embeddings to LLM space
+
+## Model
+
+- HuggingFace: [Vikhrmodels/Borealis-5b-it](https://huggingface.co/Vikhrmodels/Borealis-5b-it)
+
+## Note
+
+This plugin is experimental. For production use, consider using the standard transformers implementation.