diff --git a/cpp/tensorrt_llm/thop/allreduceOp.cpp b/cpp/tensorrt_llm/thop/allreduceOp.cpp
index fe95722ab5dc..06332fc50407 100644
--- a/cpp/tensorrt_llm/thop/allreduceOp.cpp
+++ b/cpp/tensorrt_llm/thop/allreduceOp.cpp
@@ -563,19 +563,29 @@ class AllreduceOp
             inputPtr = windowBuffer0.ptr;
         }
 
-        // Use window-backed output buffer
-        auto [normOut, windowBuffer1] = createNCCLWindowTensor(rawComm, input.sizes(), input.scalar_type());
-        torch::Tensor outputTensor = windowBuffer1.isValid() ? normOut : torch::empty_like(inputTensor);
-        void* outputPtr = windowBuffer1.isValid() ? windowBuffer1.ptr : outputTensor.data_ptr();
-        if (!windowBuffer1.isValid())
+        // Request an output window only when the message meets the same
+        // registration threshold used by the input path. Smaller messages use a
+        // regular output tensor and skip the window allocation path.
+        torch::Tensor outputTensor;
+        if (bufferSizeBytes >= minRegistrationThreshold)
+        {
+            auto [windowOutput, windowBuffer1] = createNCCLWindowTensor(rawComm, input.sizes(), input.scalar_type());
+            if (windowBuffer1.isValid())
+            {
+                outputTensor = windowOutput;
+            }
+        }
+        if (!outputTensor.defined())
         {
             TLLM_LOG_DEBUG(
                 "[runNCCLAllReduceSymmetric] No valid symmetric buffer available; "
                 "using plain CUDA tensor for output");
+            outputTensor = torch::empty_like(inputTensor);
         }
 
         // Perform allreduce
-        NCCLCHECK_THROW(ncclAllReduce(inputPtr, outputPtr, size, (*getDtypeMap())[mType], ncclSum, comm, stream));
+        NCCLCHECK_THROW(
+            ncclAllReduce(inputPtr, outputTensor.data_ptr(), size, (*getDtypeMap())[mType], ncclSum, comm, stream));
 
         if (mOp == AllReduceFusionOp::NONE)
         {
diff --git a/jenkins/L0_Test.groovy b/jenkins/L0_Test.groovy
index 3911a2e9151d..37c5e2efe419 100644
--- a/jenkins/L0_Test.groovy
+++ b/jenkins/L0_Test.groovy
@@ -6193,6 +6193,7 @@ def launchTestJobs(pipeline, testFilter, globalVars)
         "DGX_A100-FMHA-Post-Merge-1": ["auto:dgx-a100-x1", "l0_a100", 1, 1],
         "DGX_H100-2_GPUs-PyTorch-Others-1": ["auto:dgx-h100-x2", "l0_dgx_h100", 1, 2, 2],
         "DGX_H100-2_GPUs-PyTorch-Others-2": ["auto:dgx-h100-x2", "l0_dgx_h100", 2, 2, 2],
+        "DGX_H100-2_GPUs-PyTorch-Others-Post-Merge-1": ["auto:dgx-h100-x2", "l0_dgx_h100", 1, 1, 2],
         "DGX_H100-2_GPUs-PyTorch-GptOss-1": ["auto:dgx-h100-x2", "l0_dgx_h100", 1, 1, 2],
         "DGX_H100-2_GPUs-PyTorch-Ray-1": ["auto:dgx-h100-x2", "l0_dgx_h100", 1, 1, 2],
         "DGX_H100-4_GPUs-PyTorch-DeepSeek-1": ["auto:dgx-h100-x4", "l0_dgx_h100", 1, 1, 4],
diff --git a/tests/integration/test_lists/test-db/l0_dgx_h100.yml b/tests/integration/test_lists/test-db/l0_dgx_h100.yml
index 43ab57a68f7a..83997d5341a5 100644
--- a/tests/integration/test_lists/test-db/l0_dgx_h100.yml
+++ b/tests/integration/test_lists/test-db/l0_dgx_h100.yml
@@ -343,3 +343,19 @@ l0_dgx_h100:
   - accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_fp8_4gpus[attention_dp_off-cpp_mamba_cache]
   - accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_fp8_4gpus[attention_dp_on-python_mamba_cache]
   - accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_fp8_4gpus[attention_dp_on-cpp_mamba_cache]
+- condition:
+    ranges:
+      system_gpu_count:
+        gte: 2
+        lte: 2
+    wildcards:
+      gpu:
+      - '*h100*'
+      linux_distribution_name: ubuntu*
+    terms:
+      stage: post_merge
+      backend: pytorch
+      auto_trigger: others
+      orchestrator: mpi
+  tests:
+  - unittest/_torch/multi_gpu -m "post_merge" TIMEOUT (90)
diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt
index c3a649190f0f..72b5d5893b38 100644
--- a/tests/integration/test_lists/waives.txt
+++ b/tests/integration/test_lists/waives.txt
@@ -345,7 +345,6 @@ unittest/_torch/modeling/test_modeling_nemotron_nano_v2_vl.py::test_nemotron_nan
 unittest/_torch/modules/tests_lora_modules/test_nemotron_h_lora_sanity.py::TestNemotronHLoRA::test_lora_pp2_sanity SKIP (https://nvbugs/6428124)
 unittest/_torch/modules/tests_lora_modules/test_qwen3_sanity.py::TestQwen3LoRA::test_qwen3_fp8_lora SKIP (https://nvbugs/6668777)
 unittest/_torch/moe/test_moe_backend.py::test_moe_backend[act=Relu2-e60_k4_h2048_i1408-seq=8-dtype=torch.bfloat16-backend=TRTLLM-quant=NVFP4-routing=Renormalize] SKIP (https://nvbugs/5989912)
-unittest/_torch/multi_gpu/test_linear.py::test_row_linear_norm_fusion[2-hidden:16-seqlen:2] SKIP (https://nvbugs/6501404)
 unittest/_torch/speculative/hw_agnostic/test_dflash.py::test_dflash_qwen3_5_4b[False] SKIP (https://nvbugs/6535767)
 unittest/_torch/speculative/hw_agnostic/test_dflash.py::test_dflash_qwen3_5_4b[True] SKIP (https://nvbugs/6535767)
 unittest/_torch/speculative/hw_agnostic/test_ngram.py::test_llama_ngram[True-True-TRTLLM] SKIP (https://nvbugs/6507102)
diff --git a/tests/unittest/_torch/multi_gpu/test_linear.py b/tests/unittest/_torch/multi_gpu/test_linear.py
index 4db1c6b053ce..3e4b40b2f57c 100644
--- a/tests/unittest/_torch/multi_gpu/test_linear.py
+++ b/tests/unittest/_torch/multi_gpu/test_linear.py
@@ -310,6 +310,7 @@ def test_row_linear(hidden_size, mpi_pool_executor):
         assert r is True
 
 
+@pytest.mark.post_merge
 @pytest.mark.skipif(torch.cuda.device_count() < 2,
                     reason='needs 2 GPUs to run this test')
 @pytest.mark.parametrize("seq_len", [2, 32], ids=lambda x: f"seqlen:{x}")