Add --speculative-moe-runner-backend server arg (#10183)

docs/advanced_features/server_arguments.md

@@ -258,6 +258,7 @@ Please consult the documentation below and [server_args.py](https://github.com/s
 | `--speculative-accept-threshold-acc` | The accept probability of a draft token is raised from its target probability p to min(1, p / threshold_acc). | `1.0` | Type: float |
 | `--speculative-token-map` | The path of the draft model's small vocab table. | `None` | Type: str |
 | `--speculative-attention-mode` | Attention backend for speculative decoding operations (both target verify and draft extend). Can be one of 'prefill' (default) or 'decode'. | `prefill` | `prefill`, `decode` |
+| `--speculative-moe-runner-backend` | MOE backend for EAGLE speculative decoding, see --moe-runner-backend for options. Same as moe runner backend if unset. | None |
 
 ## Ngram speculative decoding
 | Argument | Description | Defaults | Options |

docs/references/environment_variables.md

@@ -67,7 +67,7 @@ SGLang supports various environment variables that can be used to configure its
 | `SGLANG_FORCE_FP8_MARLIN` | Force using FP8 MARLIN kernels even if other FP8 kernels are available | `false` |
 | `SGLANG_ENABLE_FLASHINFER_GEMM` | Use flashinfer kernels when running blockwise fp8 GEMM on Blackwell GPUs | `false` |
 | `SGLANG_SUPPORT_CUTLASS_BLOCK_FP8` | Use Cutlass kernels when running blockwise fp8 GEMM on Hopper or Blackwell GPUs | `false` |
-| `SGLANG_CUTLASS_MOE` | Use Cutlass FP8 MoE kernel on Blackwell GPUs | `false` |
+| `SGLANG_CUTLASS_MOE` (deprecated) | Use Cutlass FP8 MoE kernel on Blackwell GPUs (deprecated, use --moe-runner-backend=cutlass) | `false` |
 
 
 ## Distributed Computing