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
SGLangVerified on X
@sgl_project
Part of a thread · earlier post
Source: SGLang · x.comPublished
