x.comthreadSGLang (@sgl_project) on X
SGLang announces Day-0 support for Mistral Large 4 ("Le Chonk"), saying it is the first engine to serve the model on NVIDIA Vera Rubin. The post describes the model as Mistral's largest to date: a natively multimodal 1T-parameter mixture-of-experts model covering instruct, reasoning, coding and agentic workflows. The fetched text is truncated, so benchmark claims and launch commands are not visible.
TL;DR SGLang announces Day-0 serving of Mistral Large 4, a 1T multimodal MoE, on NVIDIA Vera Rubin.
Organisations named here
- Mistral AI
- NVIDIA
- Mistral
- SGLang
- SGLang project
Technologies named here
- SGLang
- Mistral Large 4
- Mixture of Experts
Related in inference
arxiv.orgpaperMinimally Invasive Steering of Language Models
x.comthreadSamuel Zeng (@SamuelZengML) on X
huggingface.coarticle