Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A framework for efficient model inference with omni-modality models
| Date | Stars |
|---|---|
| 2026-07-30 | 5720 |
| 2026-08-07 | 5931 |
| 2026-08-15 | 6122 |
| 2026-08-18 | 6147 |
| 2026-08-19 | 6170 |
| 2026-08-20 | 6194 |
| 2026-08-21 | 6217 |
| 2026-08-22 | 6236 |
| 2026-08-23 | 6260 |
| 2026-08-24 | 6289 |
| 2026-08-25 | 6316 |
| 2026-08-26 | 6354 |
| 2026-08-27 | 6392 |
| 2026-08-28 | 6424 |
| 2026-08-29 | 6449 |
| 2026-08-30 | 6473 |
| 2026-08-31 | 6504 |
| 2026-09-01 | 6531 |
| 2026-09-02 | 6573 |
| 2026-09-03 | 6613 |
| 2026-09-04 | 6654 |
| 2026-09-05 | 6667 |
| 2026-09-06 | 6682 |
| 2026-09-07 | 6697 |
| 2026-09-08 | 6714 |
| 2026-09-09 | 6735 |
| 2026-09-10 | 6750 |
| 2026-09-11 | 6767 |
| 2026-09-12 | 6769 |
| 2026-09-13 | 6781 |
| 2026-09-14 | 6789 |
| 2026-09-15 | 6804 |
| 2026-09-16 | 6819 |
| 2026-09-17 | 6845 |
| 2026-09-18 | 6875 |
| 2026-09-19 | 6898 |
| 2026-09-20 | 6922 |
| 2026-09-21 | 6958 |
| 2026-09-22 | 6992 |
| 2026-09-23 | 7020 |
| 2026-09-24 | 7050 |
| 2026-09-25 | 7062 |
| 2026-09-26 | 7068 |
| 2026-09-27 | 7083 |
| 2026-09-28 | 7105 |
| 2026-09-29 | 7131 |
| 2026-09-30 | 7149 |
| 2026-10-01 | 7166 |
| 2026-10-02 | 7024 |
| 2026-10-03 | 7032 |
| 2026-10-04 | 7042 |
| 2026-10-05 | 7051 |
| 2026-10-06 | 7056 |
| 2026-10-07 | 7066 |
| 2026-10-08 | 7079 |
| 2026-10-09 | 7100 |
| 2026-10-10 | 7112 |
| 2026-10-11 | 7120 |
| 2026-10-12 | 7132 |
| 2026-10-13 | 7146 |
| 2026-10-14 | 7166 |
| 2026-10-15 | 7186 |
| 2026-10-16 | 7206 |
| 2026-10-17 | 7219 |
| 2026-10-18 | 7232 |
| 2026-10-19 | 7249 |
| 2026-10-20 | 7272 |
| 2026-10-21 | 7287 |
| 2026-10-22 | 7298 |
| 2026-10-23 | 7323 |
| 2026-10-24 | 7332 |
| 2026-10-25 | 7342 |
| 2026-10-26 | 7361 |
| 2026-10-27 | 7383 |
| 2026-10-28 | 7394 |
| 2026-10-29 | 7408 |
| 2026-10-30 | 7419 |
| 2026-10-31 | 7442 |
| 2026-11-01 | 7459 |
| 2026-11-02 | 7486 |
| 2026-11-03 | 7508 |
| 2026-11-04 | 7528 |
Today
+20 stars today
This week
+134 stars this week
This month
+477 stars this month
Momentum
249.0
growth rate 1.81%/day
<p align="center">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/logos/vllm-omni-logo.png">
<img alt="vllm-omni" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/logos/vllm-omni-logo.png" width=55%>
</picture>
</p>
<h3 align="center">
Easy, fast, and cheap omni-modality model serving for everyone
</h3>
<p align="center">
| <a href="https://vllm-omni.readthedocs.io/en/latest/"><b>Documentation</b></a> | <a href="https://deepwiki.com/vllm-project/vllm-omni"><b>DeepWiki</b></a> | <a href="https://discuss.vllm.ai"><b>User Forum</b></a> | <a href="https://slack.vllm.ai"><b>Developer Slack</b></a> | <a href="docs/assets/WeChat.jpg"><b>WeChat</b></a> | <a href="https://arxiv.org/abs/2610.09307"><b>Technical Report</b></a> | <a href="https://arxiv.org/abs/2602.02204"><b>Paper</b></a> | <a href="https://docs.google.com/presentation/d/1SV7-4AoSrnK25syLG9XmnEgC0D4lcjP7/edit?usp=sharing"><b>Slides</b></a> |
</p>
---
*Latest News* 🔥
- [2026/10] We released the [vLLM-Omni Technical Report](https://arxiv.org/abs/2610.09307), describing a unified serving runtime for text, audio, image, video, and action generation.
- [2026/09] We released [0.30.0](https://github.com/vllm-project/vllm-omni/releases/tag/v0.30.0), rebased onto vLLM 0.30.0, featuring a unified full-duplex serving framework around engine-owned sessions for [MiniCPM-o 4.5](recipes/OpenBMB/MiniCPM-o-4_5.md) and AURA, native cross-stage KV and multimodal payload transfer (Mooncake AR-to-DiT handoff and NIXL connectors), interactive world-model serving with [LingBot World](recipes/Robbyant/LingBot-World-2.0.md), and realtime [MiniMax H3](recipes/MiniMaxAI/MiniMax-H3.md) Turbo inference on NVIDIA Blackwell and Ascend 950.
- [2026/08] We released [0.28.0](https://github.com/vllm-project/vllm-omni/releases/tag/v0.28.0), featuring production-ready [MiniMax H3](recipes/MiniMaxAI/MiniMax-H3.md) serving on GPU and NPU, a unified AR/DiT paged KV cache runtime, and enhanced realtime full-duplex serving for the [MiniCPM-o series](recipes/OpenBMB/MiniCPM-o-4_5.md).
- [2026/08] [VeRL-Omni](https://github.com/verl-project/verl-omni) `v0.2.0` is released: faster diffusion RL powered by vLLM-Omni (request-level/step-wise batching with FA3), rebuilt Qwen3-Omni multimodal training (DPO & GSPO), plus LTX-2.3, Qwen-Image-Edit support and more. See the [release notes](https://github.com/verl-project/verl-omni/releases/tag/v0.2.0).
- [2026/08] We released [0.26.0](https://github.com/vllm-project/vllm-omni/releases/tag/v0.26.0) - aligned with the vLLM 0.26 release line, featuring [MiniMax H3](recipes/MiniMaxAI/MiniMax-H3.md) joint video/audio generation, an experimental full-duplex realtime runtime for [MiniCPM-o 4.5](recipes/OpenBMB/MiniCPM-o-4_5.md), distributed layerwise diffusion offload, and broader model, hardware, streaming, TTS, and quantization support.
- [2026/07] We released [0.24.0](https://github.com/vllm-project/vllm-omni/releases/tag/v0.24.0) - aligned with the vLLM 0.24 release line, expanding production-ready coverage across TTS, speech, diffusion, image/video generation, and robot-policy serving, with major Omni stage runtime refactoring, diffusion request-level batching, async output materialization, quantization/cache/memory improvements, and broad CUDA/ROCm/XPU/NPU support.
- [2026/06] Starting with [0.14.0](https://github.com/vllm-project/vllm-omni/releases/tag/v0.14.0), vLLM-Omni publishes a stable release aligned with every even-numbered upstream vLLM minor version. [0.16.0](https://github.com/vllm-project/vllm-omni/releases/tag/v0.16.0), [0.18.0](https://github.com/vllm-project/vllm-omni/releases/tag/v0.18.0), [0.20.0](https://github.com/vllm-project/vllm-omni/releases/tag/v0.20.0), and [0.22.0](https://github.com/vllm-project/vllm-omni/releases/tag/v0.22.0) continued this cadence, expanding omni and world-model support withExcerpt of 9,657 characters
Read on GitHub
111
97
96
89
Yueqian Lin · Duke University
88
Canlin Guo · MOSI, prev at Huawei · China
82
汪志鹏 · Rakuten Asia Pte Ltd · Singapore
66
59
58
Samit · HKUST · Hong Kong
55
51
50
Lancer · HUST · China
45
44
43
38
Jiangyun Zhu · @Inferact · Singapore
35
34
33
33
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c6271c6c2359fdbb, topic:inference, topic:model-serving, readme:model serving
matched fp:c6271c6c2359fdbb, topic:image-generation, readme:diffusion model
matched fp:c6271c6c2359fdbb, topic:video-generation, readme:video generation
matched fp:c6271c6c2359fdbb, topic:multimodal, readme:multimodal