SGLang(@sgl_project):We turned Qwen3.8-27B into a multimodal decision model. It beat Pokémon FireRed’s elite four and champion with sub-100 ms decisions from live game state. With SGLang’s native /v1/decisions, you can now turn LLMs and VLMs into classification and scoring models. We also added /v1/systemone so Jev-like open models can work with the TypeSafe SDK.

SGLang

@sgl_project

Run LLMs fast at any scale 🔗 Join our community For AI tech blogs & deep-dives 👉 @lmsysorg

加入 May 2025

54 正在關注 11.4K 粉絲

SGLang@sgl_project

2026.09.30 00:40

We turned Qwen3.8-27B into a multimodal decision model. It beat Pokémon FireRed’s elite four and champion with sub-100 ms decisions from live game state. With SGLang’s native /v1/decisions, you can now turn LLMs and VLMs into classification and scoring models. We also added /v1/systemone so Jev-like open models can work with the TypeSafe SDK.