// Inference & local runtime
sgl-project/sglang-omni
High Performance Serving Runtime For Interactive Super Intelligence System
Official · SGLang 项目Apache-2.0Active
01Recent releases
-
sgl-project/sglang-omni v0.1.9 Patch
[Benchmark] record half-duplex realtime endpoints over the legacy protocol by @luojiaxuan in https://github.com/sgl-project/sglang-omni/pull/2692
-
sgl-project/sglang-omni voxt-v1.16.1 Patch Desktop app
Voxt v1.16.1 fixes live transcription stalling after many dictations, runs on macOS 15 again, and speeds up Whisper and Cohere Transcribe.
-
sgl-project/sglang-omni v0.1.8 Patch
[Fix] Accept array media inputs in Qwen3 Omni preprocessing by @Silas-Zeng in https://github.com/sgl-project/sglang-omni/pull/2382
-
sgl-project/sglang-omni voxt-v1.16.0 Release Desktop app
Superseded by Voxt v1.16.1, which also runs on macOS 15 or later.
-
sgl-project/sglang-omni v0.1.7 Patch
[Qwen3-Omni] Disable the fused atomic MoE finalize for the talker by @0xjeffro in https://github.com/sgl-project/sglang-omni/pull/2230
02Same category
All repos →
ggml-org/llama.cpp LLM inference in C/C++ Inference & local runtime · official★ 132k 
vllm-project/vllm A high-throughput and memory-efficient inference and serving engine for LLMs Inference & local runtime · official★ 94.9k 
mudler/LocalAI LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. Inference & local runtime★ 49.8k 
exo-explore/exo Run frontier AI locally. Inference & local runtime★ 48.0k 
ray-project/ray Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads. Inference & local runtime★ 44.1k