[Fix] Adjust use_aclgraph logic (#2156)

### What this PR does / why we need it?
Updates the FusedMoE method to determine whether to use ACL Graph based
on the `torchair_graph_config`

This is equivalent to #2154 on v0.9.1-dev.

### Does this PR introduce _any_ user-facing change?
None.

### How was this patch tested?
None needed.

- vLLM version: v0.10.0
- vLLM main:
ad57f23f6a

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>

vllm_ascend/ops/fused_moe.py

@@ -1105,7 +1105,7 @@ class AscendUnquantizedFusedMoEMethod(UnquantizedFusedMoEMethod):
         # this is a naive implementation for experts load balance so as
         # to avoid accumulating too much tokens on a single rank.
         # currently it is only activated when doing profile runs.
-        if enable_force_load_balance:
+        if enable_force_load_balance and not self.use_aclgraph:
             topk_ids = torch.randint_like(topk_ids, 0, global_num_experts)
 
         fused_moe_state = get_forward_context().fused_moe_state