[Bugfix] [MoE] fix error in deepseek when using allgather (#3824)

### What this PR does / why we need it?
After refactoring vllm_ascend/models and FusedMoE, we are unable to pass
`gate` from deepseekv2.py to `AscendFusedMoE.forward`, which will result
in error when running deepseek v3/r1 with allgather.
Hence, this pr removes `gate` related computations from FusedMoE module
in eager/aclgraph mode.
### Does this PR introduce _any_ user-facing change?
`rm_router_logits` is deprecated in eager/aclgraph.
### How was this patch tested?
e2e & ut

- vLLM version: v0.11.0rc3
- vLLM main:
https://github.com/vllm-project/vllm/commit/releases/v0.11.1

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>

vllm_ascend/torchair/ops/torchair_fused_moe.py

@@ -48,12 +48,12 @@ from vllm_ascend.eplb.core.eplb_utils import (determine_default_expert_map,
 from vllm_ascend.ops.expert_load_balancer import ExpertLoadBalancer
 from vllm_ascend.quantization.quant_config import AscendFusedMoEMethod
 from vllm_ascend.torchair.ops.sequence_parallel import MetadataForPadding
-from vllm_ascend.torchair.utils import (npu_stream_switch, npu_wait_tensor,
+from vllm_ascend.torchair.utils import (get_all_reduce_merge_state,
+                                        get_rm_router_logits_state,
+                                        npu_stream_switch, npu_wait_tensor,
                                         super_kernel)
 from vllm_ascend.utils import (AscendSocVersion, dispose_tensor,
-                               get_all_reduce_merge_state,
-                               get_ascend_soc_version,
-                               get_rm_router_logits_state, is_310p,
+                               get_ascend_soc_version, is_310p,
                                is_hierarchical_communication_enabled,
                                vllm_version_is)
 

vllm_ascend/torchair/utils.py

@@ -15,6 +15,8 @@ try:
 except ImportError:
     from torchair.ops import NpuStreamSwitch as _npu_stream_switch
     from torchair.ops import npu_wait_tensor as _npu_wait_tensor
+
+import vllm_ascend.envs as envs_ascend
 from vllm_ascend.utils import ACL_FORMAT_FRACTAL_NZ, is_enable_nz
 
 KV_CACHE_BYTES_CACHE_PATH_NAME = ".kv_cache_bytes"
@@ -238,3 +240,33 @@ def torchair_ops_patch():
 
 def super_kernel(prefix: str, option: str, enabled: bool = True):
     return _super_kernel(prefix, option) if enabled else nullcontext()
+
+
+# TODO(ttanzhiqiang): rm_router_logits
+# dp>1 will trigger
+# In theory, this solution is only applicable to AllGather and AllGatherEP, because in the dp scenario, the previous operation was gate + two communications, and now it is changed to one communication + gate operation, which can save some communication time. In theory, all moe AllGather and AllGatherEP solutions can follow this logic, but now other moe models (qwen3-235b) dp solutions are not adjusted, so use the switch to control it to prevent code errors.
+def get_rm_router_logits_state(ep_size: int, dp_size: int,
+                               is_deepseek_v3_r1: bool):
+    # the fusion operator torch_npu.npu_grouped_matmul_finalize_routing called by allgather ep
+    # only supports deepseek v3/r1
+    if dp_size > 1:
+        if (envs_ascend.VLLM_ENABLE_FUSED_EXPERTS_ALLGATHER_EP and ep_size > 1
+                and is_deepseek_v3_r1):
+            return True
+        elif ep_size == 1 and is_deepseek_v3_r1:
+            return True
+    return False
+
+
+# TODO(ttanzhiqiang): all_reduce merge
+# When all_reduce_merge is in progress, shared_experts does not do all_reduce in mlp, but waits until shared_experts+router_experts are completed before doing all_reduce
+# Currently, all_reduce_merge is enabled by default in the AllGather, AllGatherEP and NaiveMulticast scenarios of the deepseek model.
+def get_all_reduce_merge_state(ep_size: int, is_deepseek_v3_r1: bool):
+    # the fusion operator torch_npu.npu_grouped_matmul_finalize_routing called by allgather ep
+    # only supports deepseek v3/r1
+    if (envs_ascend.VLLM_ENABLE_FUSED_EXPERTS_ALLGATHER_EP and ep_size > 1
+            and is_deepseek_v3_r1):
+        return True
+    elif ep_size == 1 and is_deepseek_v3_r1:
+        return True
+    return False