[Readme] EPLB Support Scenarios (#4315)

### What this PR does / why we need it?
Add information on the scope of EPLB support.

---------

Signed-off-by: shenchuxiaofugui <[email protected]>

Author: shenchuxiaofugui

docs/source/user_guide/feature_guide/eplb_swift_balancer.md

@@ -12,6 +12,13 @@ Expert balancing for MoE models in LLM serving is essential for optimal performa
 - Adaptive Scaling: Automatically adjusts to workload fluctuations while maintaining stable performance.
 - Fault Tolerance: Redundant expert placement ensures system resilience during hardware failures.
 
+## Support Scenarios
+
+### Models:
+DeepseekV3/V3.1/R1、Qwen3-MOE
+### MOE QuantType:
+W8A8-dynamic
+
 ## How to Use EPLB
 
 ### Dynamic EPLB

vllm_ascend/ops/common_fused_moe.py

@@ -38,6 +38,8 @@
 from vllm_ascend.ops.expert_load_balancer import ExpertLoadBalancer
 from vllm_ascend.ops.moe.experts_selector import select_experts
 from vllm_ascend.ops.moe.moe_comm_method import setup_moe_comm_method
+from vllm_ascend.quantization.w8a8_dynamic import \
+    AscendW8A8DynamicFusedMoEMethod
 from vllm_ascend.utils import (ACL_FORMAT_FRACTAL_NZ, enable_sp, is_310p,
                                is_enable_nz, npu_stream_switch,
                                shared_expert_dp_enabled,
@@ -247,6 +249,11 @@ def __init__(self, *args, **kwargs):
             self.moe_load = torch.zeros(local_num_experts,
                                         dtype=torch.int64).npu()
 
+        eplb_enable = self.dynamic_eplb or (self.expert_map_path is not None)
+        if eplb_enable and (not isinstance(self.quant_method,
+                                           AscendW8A8DynamicFusedMoEMethod)):
+            raise ValueError("Eplb supports only w8a8_dynamic quantization.")
+
         self.moe_config.num_experts = self.global_num_experts
         self.moe_config.num_local_experts = self.local_num_experts
         self.moe_config.original_num_experts = num_experts