[CI] [AMD] miles-nightly: Split the 8-GPU suite into two jobs (#46750)

.github/workflows/nightly-test-amd-miles-rocm10-mi30x.yml

@@ -25,6 +25,7 @@ concurrency:
 jobs:
   test-miles-mi30x:
     if: github.repository == 'sgl-project/sglang'
+    name: test-miles-mi30x (${{ matrix.suite }}, ${{ matrix.runner }}${{ matrix.partition_size && format(', part {0}', matrix.part) || '' }})
     strategy:
       fail-fast: false
       matrix:
@@ -41,15 +42,26 @@ jobs:
             skip_tests: >-
               tests/e2e/sglang/test_session_server_multi_role/test_qwen38small.py
               tests/e2e/megatron/model_scripts/test_glm5_2_744b_a40b_5layer_ci.py
-          # The 4- and 8-GPU suites run past 180 min on MI300X; they take ~155 and ~112 min on MI355X.
+          # The 4- and 8-GPU suites run past 180 min on MI300X; the 4-GPU suite takes ~155 min on MI355X.
           - suite: nightly-stage-c-4-gpu-mi350
             runner: linux-mi300-4gpu-sglang
             timeout: 300
             skip_tests: ""
+          # The 8-GPU suite no longer finishes in 300 min on MI300X; split it in two.
           - suite: nightly-stage-c-8-gpu-mi350
             runner: linux-mi300-8gpu-sglang
             timeout: 300
             skip_tests: ""
+            partition_id: 0
+            partition_size: 2
+            part: 1/2
+          - suite: nightly-stage-c-8-gpu-mi350
+            runner: linux-mi300-8gpu-sglang
+            timeout: 300
+            skip_tests: ""
+            partition_id: 1
+            partition_size: 2
+            part: 2/2
     runs-on: ${{ matrix.runner }}
     steps:
       - name: Checkout code
@@ -107,6 +119,7 @@ jobs:
             -e PYTHONPATH=/root/miles:/opt/tilelang \
             -e GITHUB_STEP_SUMMARY=/sglang-checkout/github_summary.md \
             python3 tests/ci/run_suite.py --hw rocm --suite ${{ matrix.suite }} --cadence nightly \
+            ${{ matrix.partition_size && format('--auto-partition-id {0} --auto-partition-size {1}', matrix.partition_id, matrix.partition_size) || '' }} \
             ${{ (github.event_name != 'workflow_dispatch' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           cat "${GITHUB_WORKSPACE}/github_summary.md" >> "$GITHUB_STEP_SUMMARY" || true
           exit ${TEST_EXIT_CODE}

.github/workflows/nightly-test-amd-miles-rocm10.yml

@@ -46,8 +46,18 @@ jobs:
             partition_id: 1
             partition_size: 2
             part: 2/2
+          # The 8-GPU suite grew to ~6.5 h of estimated test time and no longer
+          # finishes in the step timeout; split it the same way.
           - suite: nightly-stage-c-8-gpu-mi350
             runner: linux-mi35x-gpu-8
+            partition_id: 0
+            partition_size: 2
+            part: 1/2
+          - suite: nightly-stage-c-8-gpu-mi350
+            runner: linux-mi35x-gpu-8
+            partition_id: 1
+            partition_size: 2
+            part: 2/2
     runs-on: ${{ matrix.runner }}
     steps:
       - name: Checkout code