sgl-project/sglang-omni
SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #44 of 2,845 repositories GStars tracks this week (top 2%).
5 releases in the last 90 days, the latest 3 days ago, with 147 contributors on GitHub.
Use Cases & Benefits
- Provides a high-performance multi-stage serving framework for audio, speech, and unified multimodal models including TTS and ASR.
- Enables efficient, transport-aware execution with stage-specialized scheduling and OpenAI-compatible API endpoints for diverse audio model serving.
- Use for deploying scalable text-to-speech and speech recognition services with streaming and batch processing capabilities.
- Use for integrating multimodal chat and audio generation models supporting heterogeneous hardware like NVIDIA CUDA and Intel GPUs.
- Use for building music generation pipelines that convert lyrics and captions into high-quality stereo audio using advanced model orchestration.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
⭐ Star SGLang-Omni to help more builders discover open infrastructure for multimodal and speech serving!
SGLang-Omni is a multi-stage serving runtime for omni, speech, and TTS models. Its design target is multi-stage decoding: generation split across heterogeneous stages with different compute patterns, dependency structures, and resource needs. SGLang-Omni owns the pipeline topology, stage lifecycle, inter-stage transport, model-family integration layer, and OpenAI-compatible serving surface, while composing with SGLang for high-performance autoregressive scheduling and model execution where applicable.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+699 stars over 62 days across 7 snapshot days; best day +4 on Aug 16.
Forks
603+262
Open issues
853+417
Compared with peers in Machine Learning
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 11, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| pytorch/pytorch | 105.0K | +449 | 64 | 23 days ago |
| openbq-org/OpenBB | 74.2K | +0 | 75 | 14 days ago |
| apache/airflow | 47.2K | +0 | 75 | 27 days ago |
| nautechsystems/nautilus_trader | 30.6K | +0 | 75 | 7 days ago |
| GeeeekExplorer/nano-vllm | 15.8K | +0 | 75 | — |
| sgl-project/sglang-omni | 1.5K | +0 | 55 | 3 days ago |
| Category median | 47.2K | +0 | 75 | — |
Also by sgl-project
Other repositories from this maintainer that GStars tracks
Discover Repositories
Search across tracked repositories by name or description