vLLM

Overview

vLLM is an OpenAI-compatible provider for self-hosted inference. Use it through DeepIntShield with the standard OpenAI-compatible request format. Key characteristics:

• OpenAI compatibility - Chat, text completions, embeddings, rerank, and streaming
• Self-hosted - Typically runs at https://vllm.example.com or your own server
• Optional authentication - API key often omitted for local instances
• Responses API - Supported via chat completion fallback

Supported Operations

Operation	Non-Streaming	Streaming	Endpoint
Chat Completions	✅	✅	/v1/chat/completions
Responses API	✅	✅	/v1/chat/completions
Text Completions	✅	✅	/v1/completions
Embeddings	✅	-	/v1/embeddings
Rerank	✅	-	/v1/rerank (fallback: /rerank)
List Models	✅	-	/v1/models
Image Generation	❌	❌	-
Speech (TTS)	❌	❌	-
Transcriptions (STT)	✅	✅	/v1/audio/transcriptions
Files	❌	❌	-
Batch	❌	❌	-

Note

Unsupported Operations (❌): Image Generation, Speech, Files, and Batch are not supported and return an unsupported-operation error.

---

Authentication

• API key: Optional. For local vLLM instances, the key is often left empty.
• When set, the key is sent as Authorization: Bearer <key>.

---

Configuration

• Base URL: Point this to your vLLM instance (e.g. https://vllm.example.com) via the provider network_config.base_url.
• Model names: Depend on the models loaded in your vLLM instance (e.g. meta-llama/Llama-3.2-1B-Instruct, BAAI/bge-m3 for embeddings).

curl -X POST https://app.deepintshield.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "x-bf-vk: $DEEPINTSHIELD_VIRTUAL_KEY" \
  -d '{
    "model": "vllm/meta-llama/Llama-3.2-1B-Instruct",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

---

Getting started

1. Run a vLLM server (Docker or pip). Example with Docker:

   docker run --gpus all -p 8000:8000 vllm/vllm-openai:latest --model meta-llama/Llama-3.2-1B-Instruct

2. Verify the server:

   curl https://vllm.example.com/v1/models

3. Use DeepIntShield with model prefix vllm/<model_id> (e.g. vllm/meta-llama/Llama-3.2-1B-Instruct).

---

1. Chat Completions

vLLM supports standard OpenAI chat completion parameters. For full parameter reference, see OpenAI Chat Completions. Message types, tools, and streaming follow the same behavior.

---

2. Responses API

vLLM supports the Responses API with the same parameters as Chat Completions.

---

3. Text Completions

Parameter	Mapping
prompt	Sent as-is
max_tokens	max_tokens
temperature	temperature
top_p	top_p
stop	stop sequences

---

4. Embeddings

vLLM supports /v1/embeddings. Use model IDs exposed by your vLLM server (e.g. BAAI/bge-m3).

---

5. List Models

Lists models from your vLLM instance via /v1/models. Available models depend on what is loaded on the server.

---

6. Rerank

vLLM supports reranking for pooling/cross-encoder reranker models. DeepIntShield sends requests to /v1/rerank and automatically falls back to /rerank when required by your vLLM deployment.

curl -X POST https://app.deepintshield.com/v1/rerank \
  -H "Authorization: Bearer sk-bf-your-virtual-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vllm/BAAI/bge-reranker-v2-m3",
    "query": "What is machine learning?",
    "documents": [
      {"text": "Machine learning is a subset of AI."},
      {"text": "Python is a programming language."},
      {"text": "Deep learning uses neural networks."}
    ],
    "params": {
      "return_documents": true
    }
  }'

Note

Your upstream vLLM server must be started with a rerank-capable model (pooling/cross-encoder task support).

---

Caveats

Base URL must be configured

Severity: Low
Behavior: The base URL points to your vLLM instance (e.g. https://vllm.example.com).
Impact: For remote or custom ports, set network_config.base_url in the provider config.

Error responses with HTTP 200

Severity: Low
Behavior: vLLM may return HTTP 200 with an error payload (e.g. {"error": {"code": 404, "message": "..."}}) instead of 4xx/5xx.
Impact: DeepIntShield normalizes these into standard error responses so clients see consistent error handling.