[NVIDIA] Change to use `num_local_experts` (#8453)

docs/backend/server_arguments.md

@@ -214,7 +214,8 @@ Please consult the documentation below and [server_args.py](https://github.com/s
 | `--ep-size` | The expert parallelism size. | 1 |
 | `--enable-ep-moe` | Enabling expert parallelism for moe. The ep size is equal to the tp size. | False |
 | `--enable-deepep-moe` | Enabling DeepEP MoE implementation for EP MoE. | False |
-| `--enable-flashinfer-moe` | Enabling Flashinfer MoE implementation. | False |
+| `--enable-flashinfer-cutlass-moe` | Enabling Flashinfer Cutlass MoE implementation for high throughput. | False |
+| `--enable-flashinfer-trtllm-moe` | Enabling Flashinfer Trtllm MoE implementation for low latency. | False |
 | `--deepep-mode` | Select the mode when enable DeepEP MoE, could be `normal`, `low_latency` or `auto`. Default is `auto`, which means `low_latency` for decode batch and `normal` for prefill batch. | auto |
 | `--ep-num-redundant-experts` | Allocate this number of redundant experts in expert parallel. | 0 |
 | `--ep-dispatch-algorithm` | The algorithm to choose ranks for redundant experts in expert parallel. | None |

python/sglang/srt/layers/moe/ep_moe/layer.py

@@ -1268,7 +1268,7 @@ class FlashInferEPMoE(EPMoE):
             topk_group=self.topk_group,
             intermediate_size=self.w2_weight.shape[2],
             local_expert_offset=self.start_expert_id,
-            local_num_experts=self.num_experts_per_partition,
+            local_num_experts=self.num_local_experts,
             routed_scaling_factor=self.routed_scaling_factor,
             tile_tokens_dim=_get_tile_tokens_dim(
                 hidden_states.shape[0], self.top_k, self.num_experts