Skip to content
View original post on X: SGLangOfficial· 25/100AI score25/100

SGLang publishes a cookbook for StepFun's Step-5-Preview model

AISummary

SGLang (@sgl_project) shares a cookbook for running StepFun's Step-5-Preview model. The guide covers a B300 setup with tensor parallelism of 4, FP8 quantization, TensorRT-LLM MoE, and MTP speculative decoding, with HiCache off and bf16 KV cache.

Post on XView on X

Source: SGLang · x.comPublished