RadixArk
@radixark
GLM-5.2 on SGLang was battle-tested and is currently serving hundreds of thousands of people in production with our partners. GLM-5.3 carries all the great things we built for it👏
We've added an experimental NVFP4 checkpoint for GLM-5.3, and Miles support for GLM-5.3 is on the
We've added an experimental NVFP4 checkpoint for GLM-5.3, and Miles support for GLM-5.3 is on the
huggingface.coRadixArk/GLM-5.3-NVFP4 · Hugging Face
SGLang@sgl_project · Aug 28GLM-5.3 weights from @Zai_org are live, with SGLang powering day-0 serving support!
GLM-5.3 inherits every optimization and feature we battle-tested for GLM-5.2 over the past months.
On real-world multi-turn agentic workloads, we measured 537.6 tok/s/user on NVFP4 and 413
GLM-5.3 inherits every optimization and feature we battle-tested for GLM-5.2 over the past months.
On real-world multi-turn agentic workloads, we measured 537.6 tok/s/user on NVFP4 and 413
0:21 3 37