diff --git a/.github/workflows/nightly-test-amd-rocm720.yml b/.github/workflows/nightly-test-amd-rocm720.yml
index 6b8622c8d..3c3983115 100644
--- a/.github/workflows/nightly-test-amd-rocm720.yml
+++ b/.github/workflows/nightly-test-amd-rocm720.yml
@@ -79,6 +79,7 @@ on:
           # 8-GPU Qwen 3.5 (MI30x + MI35x)
           - nightly-8-gpu-qwen35-rocm720
           - nightly-8-gpu-mi35x-qwen35-rocm720
+          - nightly-8-gpu-mi35x-qwen35-triton-dcp-rocm720
           # 8-GPU GLM-5.1 (MI30x + MI35x)
           - nightly-8-gpu-glm51-rocm720
           - nightly-8-gpu-mi35x-glm51-rocm720
@@ -1660,6 +1661,40 @@ jobs:
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
+  nightly-8-gpu-mi35x-qwen35-triton-dcp-rocm720:
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (!(inputs.job_filter || inputs.job_select) || (inputs.job_filter || inputs.job_select) == 'all' || contains(format(',{0},', inputs.job_filter || inputs.job_select), ',nightly-8-gpu-mi35x-qwen35-triton-dcp-rocm720,'))
+    runs-on: linux-mi35x-gpu-8
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.sha }}
+
+      - name: Ensure VRAM is clear
+        run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
+
+      - name: Setup docker (ROCm 7.2)
+        run: |
+          touch github_summary.md
+          bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
+        env:
+          GITHUB_WORKSPACE: ${{ github.workspace }}
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
+          bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
+
+      - name: Accuracy Test MI35x ROCm 7.2 (8-GPU Qwen 3.5 Triton DCP)
+        timeout-minutes: 120
+        run: |
+          > github_summary.md  # Clear summary file
+          bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-qwen35-triton-dcp --nightly --timeout-per-file 7200 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
+          echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
+          exit ${TEST_EXIT_CODE:-0}
+
   # ==============================================================================
   # 8-GPU GLM-5.1 (MI30x + MI35x)
   # ==============================================================================
@@ -1991,6 +2026,7 @@ jobs:
       # 8-GPU Qwen 3.5 (MI30x + MI35x)
       - nightly-8-gpu-qwen35-rocm720
       - nightly-8-gpu-mi35x-qwen35-rocm720
+      - nightly-8-gpu-mi35x-qwen35-triton-dcp-rocm720
       # 8-GPU GLM-5.1 (MI30x + MI35x)
       - nightly-8-gpu-glm51-rocm720
       - nightly-8-gpu-mi35x-glm51-rocm720
diff --git a/.github/workflows/nightly-test-amd.yml b/.github/workflows/nightly-test-amd.yml
index ce39c91cd..74737886b 100644
--- a/.github/workflows/nightly-test-amd.yml
+++ b/.github/workflows/nightly-test-amd.yml
@@ -75,6 +75,7 @@ on:
           # 8-GPU Qwen 3.5 (MI30x + MI35x)
           - nightly-8-gpu-qwen35
           - nightly-8-gpu-mi35x-qwen35
+          - nightly-8-gpu-mi35x-qwen35-triton-dcp
           # 8-GPU GLM-5.1 (MI30x + MI35x)
           - nightly-8-gpu-glm51
           - nightly-8-gpu-mi35x-glm51
@@ -1514,6 +1515,40 @@ jobs:
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
+  nightly-8-gpu-mi35x-qwen35-triton-dcp:
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (!(inputs.job_filter || inputs.job_select) || (inputs.job_filter || inputs.job_select) == 'all' || contains(format(',{0},', inputs.job_filter || inputs.job_select), ',nightly-8-gpu-mi35x-qwen35-triton-dcp,'))
+    runs-on: linux-mi35x-gpu-8
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.sha }}
+
+      - name: Ensure VRAM is clear
+        run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
+
+      - name: Setup docker
+        run: |
+          touch github_summary.md
+          bash scripts/ci/amd/amd_ci_start_container.sh
+        env:
+          GITHUB_WORKSPACE: ${{ github.workspace }}
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/amd/amd_ci_install_dependency.sh
+          bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
+
+      - name: Accuracy Test MI35x (8-GPU Qwen 3.5 Triton DCP)
+        timeout-minutes: 120
+        run: |
+          > github_summary.md  # Clear summary file
+          bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-qwen35-triton-dcp --nightly --timeout-per-file 7200 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
+          echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
+          exit ${TEST_EXIT_CODE:-0}
+
   # ==============================================================================
   # 8-GPU GLM-5.1 (MI30x + MI35x)
   # ==============================================================================
@@ -1841,6 +1876,7 @@ jobs:
       # 8-GPU Qwen 3.5 (MI30x + MI35x)
       - nightly-8-gpu-qwen35
       - nightly-8-gpu-mi35x-qwen35
+      - nightly-8-gpu-mi35x-qwen35-triton-dcp
       # 8-GPU GLM-5.1 (MI30x + MI35x)
       - nightly-8-gpu-glm51
       - nightly-8-gpu-mi35x-glm51
diff --git a/test/registered/amd/test_qwen3p5_triton_dcp.py b/test/registered/amd/test_qwen3p5_triton_dcp.py
index ec2379b9c..4536dd012 100644
--- a/test/registered/amd/test_qwen3p5_triton_dcp.py
+++ b/test/registered/amd/test_qwen3p5_triton_dcp.py
@@ -14,7 +14,9 @@ from sglang.test.test_utils import (
 )
 
 register_amd_ci(
-    est_time=4800, suite="nightly-amd-accuracy-8-gpu-mi35x-qwen35", nightly=True
+    est_time=4800,
+    suite="nightly-amd-accuracy-8-gpu-mi35x-qwen35-triton-dcp",
+    nightly=True,
 )
 
 QWEN35_MODEL_PATH = os.environ.get("QWEN3_5_MODEL_PATH", "Qwen/Qwen3.5-397B-A17B-FP8")