# vLLM — developer ecosystem report

- GitHub org: `vllm-project`
- Category: ai
- Overall score: 63.0 / 100
- Overall rank: #42
- Last refreshed: 2026-08-24

## Pillar scores

| Pillar | Score / 100 | Rank | Weight in overall |
| --- | --- | --- | --- |
| Code & Polish | 81.0 | #17 | ~22% |
| Education | 72.0 | #308 | ~18% |
| AI readiness | 48.0 | #203 | part of Reach |
| Builder experience | 0.0 | #1 | ~12% |
| Community | 79.0 | #4 | ~16% |
| Reach | 23.0 | #836 | ~18% |
| Momentum | 44.0 | #300 | ~14% |

## Links

- GitHub: https://github.com/vllm-project

## Public GitHub totals

| Metric | Value |
| --- | --- |
| Repos analyzed | 12 |
| Stars | 122,874 |
| Forks | 29,873 |
| Open issues | 13,755 |
| Contributors | — |

## Top repositories

| Repo | Stars | Language | Description |
| --- | --- | --- | --- |
| [vllm](https://github.com/vllm-project/vllm) | 89,825 | Python | A high-throughput and memory-efficient inference and serving engine for LLMs |
| [vllm-omni](https://github.com/vllm-project/vllm-omni) | 6,275 | Python | A framework for efficient model inference with omni-modality models |
| [semantic-router](https://github.com/vllm-project/semantic-router) | 5,250 | Go | A programmable Mixture-of-Models router for heterogeneous LLM inference |
| [aibrix](https://github.com/vllm-project/aibrix) | 5,030 | Go | Cost-efficient and pluggable Infrastructure components for GenAI inference |
| [llm-compressor](https://github.com/vllm-project/llm-compressor) | 3,714 | Python | Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM |
| [vllm-ascend](https://github.com/vllm-project/vllm-ascend) | 2,688 | C++ | Community maintained hardware plugin for vLLM on Ascend |
| [production-stack](https://github.com/vllm-project/production-stack) | 2,517 | Python | vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization |
| [vllm-metal](https://github.com/vllm-project/vllm-metal) | 1,632 | Python | Community maintained hardware plugin for vLLM on Apple Silicon |
| [guidellm](https://github.com/vllm-project/guidellm) | 1,534 | Python | Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs |
| [recipes](https://github.com/vllm-project/recipes) | 985 | JavaScript | Common recipes to run vLLM |
| [speculators](https://github.com/vllm-project/speculators) | 754 | Python | A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM |
| [vime](https://github.com/vllm-project/vime) | 428 | Python | An LLM post-training framework with vLLM for RL Scaling |

## Methodology

Scores are computed from public signals only (GitHub, package registries, docs sites, community platforms). Pillar definitions: https://www.smoower.com/docs.md

---

HTML version: https://www.smoower.com/vllm-project
Machine index: https://www.smoower.com/llms.txt · MCP server: https://www.smoower.com/mcp · REST API: https://www.smoower.com/api/v1