sglang-omni
sglang-omni is SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models. - sgl-project/sglang-omni. It is ranked #622 on the Dev Radar, in AI dev tools, first seen 18 days ago and shared in 10 posts (26.2k views).
GitHub - sgl-project/sglang-omni: SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models. · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} sgl-project / sglang-omni Public Notifications You must be signed in to change notification settings Fork 501 Star 1.2k main Branches…
What people said about sglang-omni on X
大家好，今天我们发布了 SGLang Omni v0.1.6。本版本共合入 53 个 PR，迎来 7 位新贡献者，首次贡献者共合入 9 个 PR。新增 NVIDIA Nemotron VoiceChat-11B，支持 offline 与基于 /v1/realtime 的 live duplex speech-to-speech，并进一步扩展多模型、多硬件 serving 能力。 1.性能上持续优化 CosyVoice3、Qwen3-TTS、AuK、MOSS-TTS，覆盖 CUDA Graph、reference encoding、batching、kernel fusion 和 request hot path。…
— @GenAI_is_real, 1 days ago · 65 likes · see the post
趁热打铁，我们今天发布了 SGLang Omni V0.1.4： PyPI: https://pypi.org/project/sglang-omni/0.1.4/ Github release: https://github.com/sgl-project/sglang-omni/releases/tag/v0.1.4 1. 性能上，Qwen3-ASR、Qwen3-TTS、Qwen3-Omni、MOSS-TTS、ARK-ASR、Whisper、Fun-CosyVoice3、Ming-Omni-TTS 等核心模型完成了新一轮明显优化，覆盖 Encoder / Prefill CUDA Graph、kernel…
— @GenAI_is_real, 18 days ago · 50 likes · see the post
大家好，更迭不断，今天我们发布了 SGLang Omni v 0.1.5。共合入 88 个 PR，并迎来了 13 位新贡献者，这些首次贡献者在本版本中一共提交并合入了 16 个 PR。同时，本版本新增 1 个全新的模型家族 AuK，覆盖 AuK 和 AuK-Flash，并新增 Qwen3-TTS 1.7B CustomVoice 支持： 1. 性能上，Qwen3-TTS、MOSS-TTS、ARK-ASR、Whisper、Qwen3-Omni、Fun-CosyVoice3 等核心模型完成了显著的 serving 优化，重点改善高并发吞吐、TTFA / 延迟、CUDA Graph 覆盖和资源利用率。 2. Serving…
— @GenAI_is_real, 9 days ago · 35 likes · see the post
Alternatives to sglang-omni
- muse.ai — New connectors are live today. Come build with us.
- classifier.dev — now outperforms jev and is free
- mimo-v2.6 RL — Streaming the run
- academy.dair.ai — Chat with Paper
- Union Alpha — Union Alpha is a multimodal model built for research, coding, and agentic workflows, while delivering frontier-level…
- cua — Draft #3943
sglang-omni in numbers
- Rank on the Dev Radar: #622 of 1355
- Shared in 10 posts by 1 account: @GenAI_is_real
- 26.2k views on those posts
- First seen 18 days ago, last shared 1 days ago
- Pricing seen by Jev: open source
- Market: AI dev tools
FAQ
What is sglang-omni?
SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models. - sgl-project/sglang-omni It was first shared on X 18 days ago and is ranked #622 on the Dev Radar.
Is sglang-omni free?
It is open source.
Who shared sglang-omni?
1 account on X, including @GenAI_is_real, in 10 posts totalling 26.2k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:39 UTC. Full method.