Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. 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),
Installs just this skill. Get the whole plugin for auto-invocation.
⚡ How it fires
How this skill gets triggered: by you, by Claude, or both.
Fires itselfClaude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/inference-serving-vllm
👁️ Context preview
The summary Claude sees to decide when to auto-load this skill.
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. 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),
📊 Stats
Stars29,856
Forks3,189
LanguagePython
LicenseMIT
📦 Ships with claude-code-templates
</> SKILL.md
inference-serving-vllm.SKILL.md
---name: serving-llms-vllm
description: Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. 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.
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [vLLM, Inference Serving, PagedAttention, Continuous Batching, High Throughput, Production, OpenAI API, Quantization, Tensor Parallelism]
dependencies: [vllm, torch, transformers]
---# vLLM - High-Performance LLM Serving
## 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)
- **TensorRT-LLM**: NVIDIA-only, need absolute maximum performance
- **Text-Generation-Inference**: Already in HuggingFace ecosystem
## Common issues
**Issue: Out of memory during model loading**
Reduce memory usage:
```bash
vllm serve MODEL \
--gpu-memory-utilization 0.7 \
--max-model-len 4096
```
Or use quantization:
```bash
vllm serve MODEL --quantization awq
```
**Issue: Slow first token (TTFT > 1 second)**
Enable prefix caching for repeated prompts:
```bash
vllm serve MODEL --enable-prefix-caching
```
For long prompts, enable chunked prefill:
```bash
vllm serve MODEL --enable-chunked-prefill
```
**Issue: Model not found error**
Use `--trust-remote-code` for custom models:
```bash
vllm serve MODEL --trust-remote-code
```
**Issue: Low throughput (<50 req/sec)**
Increase concurrent sequences:
```bash
vllm serve MODEL --max-num-seqs 512
```
Check GPU utilization with `nvidia-smi` - should be >80%.
**Issue: Inference slower than expected**
Verify tensor parallelism uses power of 2 GPUs:
```bash
vllm serve MODEL --tensor-parallel-size 4 # Not 3
```
Enable speculative decoding for faster generation:
```bash
vllm serve MODEL --speculative-model DRAFT_MODEL
```
## Advanced topics
**Server deployment patterns**: See [references/server-deployment.md](references/server-deployment.md) for Docker, Kubernetes, and load balancing configurations.
**Performance optimization**: See [references/optimization.md](references/optimization.md) for PagedAttention tuning, continuous batching details, and benchmark results.
**Quantization guide**: See [references/quantization.md](references/quantization.md) for AWQ/GPTQ/FP8 setup, model preparation, and accuracy comparisons.
**Troubleshooting**: See [references/troubleshooting.md](references/troubleshooting.md) for detailed error messages, debugging steps, and performance diagnostics.
## Hardware requirements
- **Small models (7B-13B)**: 1x A10 (24GB) or A100 (40GB)
- **Medium models (30B-40B)**: 2x A100 (40GB) with tensor parallelism
- **Large models (70B+)**: 4x A100 (40GB) or 2x A100 (80GB), use AWQ/GPTQ
