# sgl-project/sglang-omni

> Serving framework for audio and multimodal models (TTS, ASR, omni) with a multi-stage runtime and OpenAI-compatible API. Used to self-host speech generation and transcription on your own GPUs.

- Magnitude: 3.4 out of 10 — Breakout
- Stars: 1,430 total · +2 stars measured 2026-10-13, 10:53–12:29 UTC, ≈ 15 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2026-01-07 · Last push: 2026-10-13
- GitHub: https://github.com/sgl-project/sglang-omni · Homepage: https://sgl-project.github.io/sglang-omni/ · Page: https://gitnova.dev/en/r/sgl-project/sglang-omni

## Useful for

- Serve text-to-speech behind an OpenAI-compatible /v1/audio/speech endpoint
- Deploy transcription with speaker diarization via /v1/audio/transcriptions
- Run Qwen3-Omni for multimodal chat with audio output

## Why it’s here

- Star-counter measurements on 2026-10-13 (UTC), 10:53–12:29: 1428 → 1430 stars (+2). This is the change over that interval.
- Estimated end-of-day forecast: about +15 stars, using observed gains and the previous day.
- Over the last two days the pace is 9.7× that of the previous week and a half.
- Elevated gains were measured on the last 2 completed UTC days in a row. Continued growth is not guaranteed.
- GitHub Trending Python today: #10, +42 stars.
- About 10 forks a day — people are taking the code.
- Recent forks include notable developers: @zRzRzRzRzRzRzR (1,718 followers).

## 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: 586
- Issues and pull requests: 2,744
- Watchers: 11
- Average over the last week: 17 per day
- Usual pace: 5 per day
- Stars in the last hour (measured): 0
- Latest release: v0.1.8 (2026-10-12)

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

2026-09-14 … 2026-10-13: 12, 13, 7, 16, 4, 4, 10, 12, 7, 8, 10, 2, 2, 5, 6, 6, 7, 0, 6, 4, 1, 1, 5, 2, 5, 4, 4, 36, 54, 2

## Spotted in now

- GitHub Trending Python today: #10, +42 stars

## More in this category

1. **open-webui/open-webui** — 7.9 · Breakout · Language models · Python · +549 stars measured 2026-10-13, 00:02–12:25 UTC, ≈ 1,025 by evening
   Open WebUI is a self-hosted web interface for AI models via Ollama and OpenAI-compatible APIs, with RAG, plugins, agents, and team collaboration.
   Full card: https://gitnova.dev/en/r/open-webui/open-webui.md
2. **lyogavin/airllm** — 7.7 · Breakout · Language models · Jupyter Notebook · +481 stars measured 2026-10-13, 00:01–12:25 UTC, ≈ 931 by evening
   A library for inference and training of large language models on low-VRAM GPUs: it streams weights layer by layer from disk, letting 70B–671B models run on 4–12 GB of VRAM without quantization or distillation.
   Full card: https://gitnova.dev/en/r/lyogavin/airllm.md
3. **microsoft/BitNet** — 6.9 · Breakout · Language models · C++ · +185 stars measured 2026-10-13, 00:02–12:25 UTC, ≈ 342 by evening
   Official inference framework for 1-bit LLMs (BitNet b1.58) with optimized kernels for CPU and GPU. Runs ternary models fast and losslessly, including a 100B model on a single CPU.
   Full card: https://gitnova.dev/en/r/microsoft/BitNet.md
4. **prabanta-dev/janas** — 6.9 · Early signal · Language models · C · +185 stars measured 2026-10-13, 01:25–12:25 UTC, ≈ 296 by evening
   Janas is a family of AI tools in C with no dependencies. Janas-LLM runs large MoE models (up to 80B, 48 GB) on a 32 GB laptop by streaming experts from NVMe SSD, and outperforms llama.cpp on all 13 tested models.
   Full card: https://gitnova.dev/en/r/prabanta-dev/janas.md
5. **mw00/project-maya** — 5.1 · Early signal · Language models · C++ · +52 stars measured 2026-10-13, 00:02–12:26 UTC, ≈ 109 by evening
   Local engine, server and dashboard to run the 321B MoE model GLM-5.3-Flash on one or two NVIDIA GPUs, offloading experts to RAM and NVMe.
   Full card: https://gitnova.dev/en/r/mw00/project-maya.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 2026-10-13 12:43 UTC, updated every 30 minutes.