diff --git a/tensorrt_llm/_torch/models/modeling_qwen3.py b/tensorrt_llm/_torch/models/modeling_qwen3.py
index 24cd6d8d418d..880aee242cd6 100644
--- a/tensorrt_llm/_torch/models/modeling_qwen3.py
+++ b/tensorrt_llm/_torch/models/modeling_qwen3.py
@@ -208,15 +208,24 @@ def __init__(self,
         config = self.model_config
         self.mapping_with_cp = mapping_with_cp
 
-        self.embed_tokens = Embedding(
-            config.pretrained_config.vocab_size,
-            config.pretrained_config.hidden_size,
-            dtype=config.pretrained_config.torch_dtype,
-            mapping=config.mapping,
-            tensor_parallel_mode=TensorParallelMode.COLUMN,
-            gather_output=True,
-            allreduce_strategy=config.allreduce_strategy,
-        )
+        # Under attention DP each rank embeds its own tokens, so the embedding
+        # is replicated like the attention-DP lm_head it may be tied to.
+        if config.mapping.enable_attention_dp and not config.mapping.enable_lm_head_tp_in_adp:
+            self.embed_tokens = Embedding(
+                config.pretrained_config.vocab_size,
+                config.pretrained_config.hidden_size,
+                dtype=config.pretrained_config.torch_dtype,
+            )
+        else:
+            self.embed_tokens = Embedding(
+                config.pretrained_config.vocab_size,
+                config.pretrained_config.hidden_size,
+                dtype=config.pretrained_config.torch_dtype,
+                mapping=config.mapping,
+                tensor_parallel_mode=TensorParallelMode.COLUMN,
+                gather_output=True,
+                allreduce_strategy=config.allreduce_strategy,
+            )
         self.layers = nn.ModuleList([
             Qwen3DecoderLayer(
                 model_config,
diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt
index 1c14893fa48f..3e8375eddc7c 100644
--- a/tests/integration/test_lists/waives.txt
+++ b/tests/integration/test_lists/waives.txt
@@ -192,7 +192,6 @@ unittest/executor/test_rpc_proxy.py SKIP (https://nvbugs/5605741)
 unittest/executor/test_rpc_worker.py SKIP (https://nvbugs/5605741)
 unittest/llmapi/test_llm_args.py::TestKvCacheManagerV2AutoResolution::test_required_v2_refuses_incompatible_disagg[nixl-cpp] SKIP (https://nvbugs/6917693)
 unittest/llmapi/test_llm_args.py::TestKvCacheManagerV2AutoResolution::test_required_v2_refuses_incompatible_disagg[ucx-python] SKIP (https://nvbugs/6917693)
-unittest/llmapi/test_llm_kv_cache_events.py::test_llm_api_attention_dp_kv_events SKIP (https://nvbugs/6891163)
 unittest/llmapi/test_llm_pytorch.py::test_gqa_nemo_lora[None] SKIP (https://nvbugs/6162504)
 unittest/llmapi/test_llm_pytorch.py::test_gqa_nemo_lora[cuda_graph_config0] SKIP (https://nvbugs/6162504)
 unittest/llmapi/test_llm_pytorch.py::test_llm_disagg_streaming_gen_cancelled[PYTHON] SKIP (https://nvbugs/6903683)