# vllm-project/vllm

> A high-throughput and memory-efficient inference and serving engine for large language models, using PagedAttention for KV-cache management. Supports 200+ model architectures and an OpenAI-compatible API.

- Magnitude: 2.8 out of 10 — Steady
- Stars: 93,326 total · +7 stars measured 2026-10-07, 11:04–12:42 UTC, ≈ 25 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2023-02-09 · Last push: 2026-10-07
- GitHub: https://github.com/vllm-project/vllm · Homepage: https://vllm.ai · Page: https://gitnova.dev/en/r/vllm-project/vllm

## Useful for

- Deploy an OpenAI-compatible server for a local LLM
- Speed up model inference with continuous batching and PagedAttention
- Serve a multimodal or MoE Hugging Face model on your own GPUs

## Why it’s here

- Star-counter measurements on 2026-10-07 (UTC), 11:04–12:42: 93319 → 93326 stars (+7). This is the change over that interval.
- Estimated end-of-day forecast: about +25 stars, using observed gains and the previous day.
- GitHub Trending Python today: #12, +73 stars.
- About 35 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 23,081
- Issues and pull requests: 59,572
- Watchers: 599
- Average over the last week: 54 per day
- Usual pace: 80 per day
- Stars in the last hour (measured): 0
- Latest release: v0.31.0 (2026-10-05)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-08 … 2026-10-07: 96, 95, 81, 75, 66, 83, 108, 101, 88, 102, 80, 70, 77, 116, 82, 107, 81, 51, 50, 59, 78, 83, 55, 62, 41, 57, 57, 60, 72, 7

## Spotted in now

- GitHub Trending Python today: #12, +73 stars

## Similar by description

1. **sgl-project/sglang** — 2.1 · Steady · Language models · Python · +12 stars measured 2026-10-07, 00:24–12:46 UTC, ≈ 23 by evening · unusual star pattern (heuristic)
   SGLang is an open-source inference framework for fast serving of large language and multimodal models, optimized for agentic workloads, RL rollouts, and large-scale deployment.
   Full card: https://gitnova.dev/en/r/sgl-project/sglang.md
2. **ggml-org/llama.cpp** — 3.4 · Steady · Language models · C++ · +52 stars measured 2026-10-07, 00:21–12:40 UTC, ≈ 104 by evening
   LLM and VLM inference implemented in C/C++ with no dependencies, running on CPUs and GPUs across many hardware backends. Enables local model execution with minimal setup and quantization.
   Full card: https://gitnova.dev/en/r/ggml-org/llama.cpp.md
3. **kvcache-ai/Mooncake** — 1.4 · Steady · Language models · C++ · +5 stars measured 2026-10-07, 00:27–12:50 UTC, ≈ 8 by evening
   LLM serving platform built on a KVCache-centric disaggregated architecture: separates prefill and decode and transfers KV cache between nodes over RDMA. Powers Kimi in production at Moonshot AI.
   Full card: https://gitnova.dev/en/r/kvcache-ai/Mooncake.md
4. **FlashML-org/FreeToken** — 2.0 · Steady · Language models · Python · +7 stars measured 2026-10-07, 00:23–12:46 UTC, ≈ 17 by evening
   A Mixture-of-Experts inference engine for running frontier-scale open-weight MoE models (290B+) on consumer hardware — GPUs, CPUs, and host memory. Aimed at users who want to run frontier models locally.
   Full card: https://gitnova.dev/en/r/FlashML-org/FreeToken.md
5. **microsoft/onnxruntime** — 1.4 · Steady · Language models · C++ · +3 stars measured 2026-10-07, 00:26–12:51 UTC, ≈ 6 by evening
   Cross-platform accelerator for ML inference and training. Runs models from PyTorch, TensorFlow, scikit-learn and others via the ONNX format with graph optimizations and hardware acceleration.
   Full card: https://gitnova.dev/en/r/microsoft/onnxruntime.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-07 12:58 UTC, updated every 30 minutes.