claudegoodies
Skill

serving-llms-vllm

From NousResearch

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Facts

Repository
NousResearch/hermes-agent
Status
Actively maintained
Last commit
Source file
skills/mlops/inference/vllm/SKILL.md

Source preview

The instructions Claude Code reads when this skill runs.

# vLLM - High-Performance LLM Serving

## When to use

Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

## Quick start

vLLM achieves 24x higher throughput than standard transformers through PagedAttention (block-based KV cache) and continuous batching (mixing prefill/decode requests).

**Installation**:
```bash
pip install vllm
```

**Basic offline inference**:
```python
from vllm import LLM, SamplingParams

llm = LLM(model="meta-llama/Llama-3-8B-Instruct")
sampling = SamplingParams(temperature=0.7, max_tokens=256)

outputs = llm.generate(["Explain quantum computing"], sampling)
print(outputs[0].outputs[0].text)
```

**OpenAI-compatible server**:
```bash
vllm serve meta-llama/Llama-3-8B-Instruct

# Query with OpenAI SDK
python -c "
from openai import OpenAI
client = OpenAI(base_url='http://localhost:8000/v1', api_key='EMPTY')
print(client.chat.completions.create(
    model='meta-llama/Llama-3-8B-Instruct',
    messages=[{'role': 'user', 'content': 'Hello!'}]
).choices[0].message.content)
"
```

## Common workflows

### Workflow 1: Production API deployment

Copy this checklist and track progress:

```
Deployment Progress:
- [ ] Step 1: Configure server settings
- [ ] Step 2: Test with limited traffic
- [ ] Step 3
View full source on GitHub →

Other skills