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…
This is a dev post classified by Jev as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.
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。 2.Serving 上新增 Nemotron VoiceChat offline / realtime 支持，并完善 streaming vocoder、realtime ASR、长音频 admission control 及高并发 request lifecycle。 3.模型与硬件上 CosyVoice3 新增 Apple Silicon MLX / MPS；Ming-Omni、Qwen3-TTS 扩展至 Ascend NPU，Qwen3-TTS 同时支持 Intel XPU 和 MUSA。 4.Runtime上新增 PD 分离与 KV page handof
Posted by Guitar Cat + LLM (14.7k followers) 1 days ago · 65 likes · 5k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: sglang-omni.
More dev work like this
- Nimble is able to process images! — @madiator
- Your agent already solved this. Finding the session is the problem. — @DanKornas
- Trains your own large language model from scratch using plain PyTorch. — @tom_doerr
- gpt 5.6 terra = gpt 6 astra — @notjazii
- your rtx 3060 was running bonsai 2 at 26 tok/s this morning and now does 40 tok/s, i… — @sudoingX
- Turning a novel into a game is more than turning chapters into dialogue. — @DanKornas
- Meet DeepSeek-V4.1-Flash: a blazing fast image-text-to-text model. It takes both images… — @HuggingModels
- How to use Jev, and where it gives you the most advantage: — @0x_rody
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 18:06 UTC. Full method.