Repository · GitHub

sgl-project/sglang-omni

SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.

Owner	sgl-project
License (as declared)	Apache-2.0
Stars	1,540
Forks	613
Main language	Python
Created	7 January 2026
Last updated at source	18 October 2026

pythonasraudio-generationcudadistributed-inferenceinferencemodel-servingmultimodalmusic-generationopenai-apipytorchsglangspeech-recognitionstreamingtext-to-speechtts

Embed this entry

<iframe src="https://silytics.si/embed/item/6ce52fed-5a89-47da-9d87-488e41cc2e47" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Stars, last 3 days

1,540 now (+21 since 2026-10-16). Counts as reported by the source, snapshotted daily by Silytics.

More from sgl-project

sglangRepository
SpecForgeRepository
rbgRepository

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.