[AMD]: docker(rocm) bump Mooncake to latest main + enable multi-protocol (#27730)

Co-authored-by: Michael <13900043+michaelzhang-ai@users.noreply.github.com>

.github/workflows/pr-test-amd.yml

@@ -1115,7 +1115,8 @@ jobs:
           echo ""
           echo "=== 5. Detect RDMA Devices for test environment ==="
           if [ -d "/sys/class/infiniband" ]; then
-            RDMA_DEVS=$(ls /sys/class/infiniband | paste -sd "," -)
+            # RDMA_DEVS=$(ls /sys/class/infiniband | paste -sd "," -)
+            RDMA_DEVS=rdma0
             echo "Detected RDMA Devices: $RDMA_DEVS"
             echo "SGLANG_TEST_RDMA_DEVICE=$RDMA_DEVS" >> $GITHUB_ENV
           else
@@ -1185,8 +1186,12 @@ jobs:
       - name: Run test_disaggregation
         timeout-minutes: 60
         run: |
+          docker exec ci_sglang rocm-smi --showtopotype || true
+          docker exec ci_sglang bash -c 'strings $(python3 -c "import mooncake,os;print(os.path.dirname(mooncake.__file__))")/engine*.so | grep -iE "rdma,hip|Unsupported multi-protocol"' || true
           bash scripts/ci/amd/amd_ci_exec.sh \
             -e SGLANG_TEST_RDMA_DEVICE="${{ env.SGLANG_TEST_RDMA_DEVICE }}" \
+            -e MC_LOG_LEVEL=TRACE \
+            -e GLOG_logtostderr=1 \
             -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-8-gpu-mi35x-disaggregation-amd --timeout-per-file 1800 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
 
   pr-test-amd-finish: