The nvidia/GLM-5-NVFP4model with NVFP4 quantization cannot be launched using the SGLang engine.

[BigCousin-z]

https://huggingface.co/nvidia/GLM-5-NVFP4，It provides this reference example, like “To serve this checkpoint with SGLang, you can start the docker lmsysorg/sglang:nightly-dev-cu13-20260305-33c92732 and run the sample command below:”， but I cannot find this image.
Where can I find this version of GLM-5 NVFP4 that works with the SGLang engine? Like Image：lmsysorg/sglang:nightly-dev-cu13-20260305-33c92732？？？？？

[b8zhong]

@BigCousin-z hi, now it is supported on main. You can try any nightly CU13 image like https://hub.docker.com/r/lmsysorg/sglang/tags here