diff --git a/docs_new/docs/advanced_features/server_arguments.mdx b/docs_new/docs/advanced_features/server_arguments.mdx index 902601797..f44b423ef 100644 --- a/docs_new/docs/advanced_features/server_arguments.mdx +++ b/docs_new/docs/advanced_features/server_arguments.mdx @@ -1208,9 +1208,9 @@ Please consult the documentation below and [server_args.py](https://github.com/s
flashinfer_cutlassauto, flashinfer_cudnn, flashinfer_cutlass, flashinfer_trtllmflashinfer_cudnn on SM120, flashinfer_cutedsl on SM100, flashinfer_cutlass otherwise), 'cutlass' (SGLang CUTLASS kernel), 'flashinfer_cutlass' (FlashInfer CUTLASS backend), 'flashinfer_cudnn' (FlashInfer cuDNN backend, optimal on CUDA 13+ with cuDNN 9.15+), 'flashinfer_cutedsl' (FlashInfer CuTe DSL backend), 'flashinfer_trtllm' (FlashInfer TensorRT-LLM backend, requires different weight preparation with shuffling). All FlashInfer backends fall back to sgl-kernel CUTLASS when FlashInfer is unavailable.autoauto, cutlass, flashinfer_cudnn, flashinfer_cutedsl, flashinfer_cutlass, flashinfer_trtllm