[AMD] AMD AITER Scout Workflow (#19467)

Co-authored-by: Bingxu Chen <Bingxu.Chen@amd.com>

.github/workflows/nightly-test-amd-rocm720.yml

@@ -10,6 +10,16 @@ on:
       - "python/sglang/version.py"
   workflow_dispatch:
     inputs:
+      aiter_ref:
+        description: 'Override AITER commit (optional, leave empty to use Dockerfile default)'
+        required: false
+        type: string
+        default: ''
+      continue_on_error:
+        description: 'Continue on error (do not fail the workflow on test failures)'
+        required: false
+        type: boolean
+        default: true
       job_filter:
         description: 'Select which job to run (leave empty or "all" to run all jobs)'
         required: false
@@ -56,11 +66,24 @@ on:
         required: false
         type: string
         default: ''
+      aiter_ref:
+        description: 'Override AITER commit (optional, leave empty to use Dockerfile default)'
+        required: false
+        type: string
+        default: ''
       job_filter:
         description: 'Select which job to run (leave empty or "all" to run all jobs)'
         required: false
         type: string
         default: 'all'
+      continue_on_error:
+        description: 'Continue on error (do not fail the workflow on test failures)'
+        required: false
+        type: boolean
+        default: true
+
+env:
+  AITER_COMMIT_OVERRIDE: ${{ inputs.aiter_ref }}
 
 concurrency:
   group: nightly-test-amd-rocm720-${{ inputs.ref || github.ref }}
@@ -86,14 +109,13 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Nightly Unit Test ROCm 7.2 (1-GPU)
         timeout-minutes: 90
         run: |
           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-1-gpu --nightly --timeout-per-file 900 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-1-gpu --nightly --timeout-per-file 900 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -116,14 +138,13 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Nightly Test ROCm 7.2 (2-GPU)
         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 --nightly --timeout-per-file 7200 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -145,15 +166,14 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Nightly Accuracy Test ROCm 7.2 (2-GPU VLM MMMU)
         timeout-minutes: 180
         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-2-gpu-vlm --nightly --timeout-per-file 7200 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-2-gpu-vlm --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -175,8 +195,7 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Performance Test ROCm 7.2 (2-GPU Text Models)
         timeout-minutes: 120
         run: |
@@ -184,7 +203,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-perf-text-2-gpu --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-perf-text-2-gpu --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -206,8 +225,7 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Performance Test ROCm 7.2 (2-GPU VLM Models)
         timeout-minutes: 180
         run: |
@@ -215,7 +233,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-perf-vlm-2-gpu --nightly --timeout-per-file 7200 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-perf-vlm-2-gpu --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -237,14 +255,14 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-test-time-deps
 
       - name: Accuracy Test ROCm 7.2 (8-GPU GPT-OSS)
         timeout-minutes: 180
         run: |
           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-gpt-oss --nightly --timeout-per-file 7200 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-gpt-oss --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -254,7 +272,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-grok1-fp8 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-grok1-fp8 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -277,7 +295,7 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-test-time-deps
 
       - name: Accuracy Test ROCm 7.2 (8-GPU Grok1-INT4)
         timeout-minutes: 60
@@ -286,7 +304,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-grok1-int4 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-grok1-int4 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -298,7 +316,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-grok1-int4 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-grok1-int4 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -320,7 +338,7 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-test-time-deps
 
       - name: Accuracy Test ROCm 7.2 (8-GPU Grok2)
         timeout-minutes: 60
@@ -329,7 +347,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-grok2 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-grok2 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -341,7 +359,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-grok2 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-grok2 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -363,7 +381,7 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-test-time-deps
 
       - name: Accuracy Test ROCm 7.2 (8-GPU DeepSeek-V3.1)
         timeout-minutes: 120
@@ -372,7 +390,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-deepseek-v31 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-deepseek-v31 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -384,7 +402,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_ROCM700A=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-deepseek-v31 --nightly --timeout-per-file 18000 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-deepseek-v31 --nightly --timeout-per-file 18000 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -406,7 +424,7 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-test-time-deps
 
       - name: Accuracy Test ROCm 7.2 (8-GPU DeepSeek-V3.2 Basic)
         timeout-minutes: 120
@@ -414,7 +432,7 @@ jobs:
           > 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-deepseek-v32 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-deepseek-v32 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -425,7 +443,7 @@ jobs:
           > 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-perf-8-gpu-deepseek-v32-basic --nightly --timeout-per-file 5400 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-deepseek-v32-basic --nightly --timeout-per-file 5400 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -447,7 +465,7 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-test-time-deps
 
       - name: Accuracy Test ROCm 7.2 (8-GPU DeepSeek-V3.2 MTP)
         timeout-minutes: 120
@@ -455,7 +473,7 @@ jobs:
           > 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-deepseek-v32-mtp --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-deepseek-v32-mtp --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -466,7 +484,7 @@ jobs:
           > 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-perf-8-gpu-deepseek-v32-mtp --nightly --timeout-per-file 7200 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-deepseek-v32-mtp --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -488,7 +506,7 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-test-time-deps
 
       - name: Accuracy Test ROCm 7.2 (8-GPU Kimi-K2.5)
         timeout-minutes: 120
@@ -496,7 +514,7 @@ jobs:
           > 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-kimi-k25 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-kimi-k25 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -518,7 +536,7 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-test-time-deps
 
       - name: Accuracy Test + Performance Test ROCm 7.2 (8-GPU Qwen3)
         timeout-minutes: 120
@@ -526,7 +544,7 @@ jobs:
           > 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-8-gpu-qwen3-235b --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-8-gpu-qwen3-235b --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -549,7 +567,7 @@ jobs:
 
       - 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_install_dependency.sh --skip-test-time-deps
           # GLM-5 requires latest transformers for glm_moe_dsa architecture
           bash scripts/ci/amd/amd_ci_exec.sh pip install git+https://github.com/huggingface/transformers.git
 
@@ -559,7 +577,7 @@ jobs:
           > 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-glm5 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-glm5 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -581,7 +599,7 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-test-time-deps
 
       - name: Accuracy Test ROCm 7.2 (8-GPU MiniMax-M2.5)
         timeout-minutes: 120
@@ -590,7 +608,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-minimax-m25 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-minimax-m25 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -614,14 +632,13 @@ jobs:
 
       - name: Install dependencies
         run: |
-          bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+          bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Nightly Test MI35x ROCm 7.2 (1-GPU)
         timeout-minutes: 90
         run: |
           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-1-gpu-mi35x --nightly --timeout-per-file 900 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-1-gpu-mi35x --nightly --timeout-per-file 900 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -644,7 +661,7 @@ jobs:
 
       - 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_install_dependency.sh --skip-test-time-deps
           # Install tabulate for run_suite.py (missing in MI35x container)
           bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
 
@@ -653,7 +670,7 @@ jobs:
         run: |
           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-8-gpu-mi35x --nightly --timeout-per-file 7200 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -676,7 +693,7 @@ jobs:
 
       - 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_install_dependency.sh --skip-test-time-deps
           # Install tabulate for run_suite.py (missing in MI35x container)
           bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
 
@@ -687,7 +704,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-grok1-int4 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-grok1-int4 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -699,7 +716,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-grok1-int4 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-grok1-int4 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -722,7 +739,7 @@ jobs:
 
       - 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_install_dependency.sh --skip-test-time-deps
           # Install tabulate for run_suite.py (missing in MI35x container)
           bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
 
@@ -733,7 +750,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-grok2 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-grok2 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -745,7 +762,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-grok2 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-grok2 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -768,7 +785,7 @@ jobs:
 
       - 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_install_dependency.sh --skip-test-time-deps
           # Install tabulate for run_suite.py (missing in MI35x container)
           bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
 
@@ -778,7 +795,7 @@ jobs:
           > 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-8-gpu-mi35x-deepseek-r1-mxfp4 --nightly --timeout-per-file 7200 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-deepseek-r1-mxfp4 --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -812,7 +829,7 @@ jobs:
 
       - 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_install_dependency.sh --skip-test-time-deps
           # Install tabulate for run_suite.py (missing in MI35x container)
           bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
 
@@ -822,7 +839,7 @@ jobs:
           > 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-8-gpu-mi35x-deepseek-v32 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-deepseek-v32 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -845,7 +862,7 @@ jobs:
 
       - 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_install_dependency.sh --skip-test-time-deps
           # Install tabulate for run_suite.py (missing in MI35x container)
           bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
 
@@ -855,7 +872,7 @@ jobs:
           > 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-deepseek-v32-mtp --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-deepseek-v32-mtp --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -878,7 +895,7 @@ jobs:
 
       - 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_install_dependency.sh --skip-test-time-deps
           # Install tabulate for run_suite.py (missing in MI35x container)
           bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
 
@@ -888,7 +905,7 @@ jobs:
           > 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-perf-8-gpu-mi35x-deepseek-v32-basic --nightly --timeout-per-file 5400 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-deepseek-v32-basic --nightly --timeout-per-file 5400 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -911,7 +928,7 @@ jobs:
 
       - 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_install_dependency.sh --skip-test-time-deps
           # Install tabulate for run_suite.py (missing in MI35x container)
           bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
 
@@ -921,7 +938,7 @@ jobs:
           > 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-kimi-k25 --nightly --timeout-per-file 7200 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-kimi-k25 --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -944,7 +961,7 @@ jobs:
 
       - 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_install_dependency.sh --skip-test-time-deps
           # Install tabulate for run_suite.py (missing in MI35x container)
           bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
 
@@ -954,7 +971,7 @@ jobs:
           > 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-8-gpu-mi35x-qwen3-235b-mxfp4 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-8-gpu-mi35x-qwen3-235b-mxfp4 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -976,7 +993,7 @@ jobs:
 
       - 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_install_dependency.sh --skip-test-time-deps
           # Install tabulate for run_suite.py (missing in MI35x container)
           bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
           # GLM-5 requires latest transformers for glm_moe_dsa architecture
@@ -988,7 +1005,7 @@ jobs:
           > 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-8-gpu-mi35x-glm5 --nightly --timeout-per-file 7200 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-glm5 --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -1011,7 +1028,7 @@ jobs:
 
       - 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_install_dependency.sh --skip-test-time-deps
           bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
 
       - name: Accuracy Test MI35x ROCm 7.2 (8-GPU MiniMax-M2.5)
@@ -1021,7 +1038,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-minimax-m25 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-minimax-m25 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -1044,7 +1061,7 @@ jobs:
 
       - 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_install_dependency.sh --skip-test-time-deps
           # Install tabulate for run_suite.py (missing in MI35x container)
           bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
 
@@ -1054,7 +1071,7 @@ jobs:
           > 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-perf-8-gpu-mi35x-deepseek-v32-mtp --nightly --timeout-per-file 7200 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-deepseek-v32-mtp --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 

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

@@ -10,6 +10,16 @@ on:
       - "python/sglang/version.py"
   workflow_dispatch:
     inputs:
+      aiter_ref:
+        description: 'Override AITER commit (optional, leave empty to use Dockerfile default)'
+        required: false
+        type: string
+        default: ''
+      continue_on_error:
+        description: 'Continue on error (do not fail the workflow on test failures)'
+        required: false
+        type: boolean
+        default: true
       job_filter:
         description: 'Select which job to run (leave empty or "all" to run all jobs)'
         required: false
@@ -56,11 +66,24 @@ on:
         required: false
         type: string
         default: ''
+      aiter_ref:
+        description: 'Override AITER commit (optional, leave empty to use Dockerfile default)'
+        required: false
+        type: string
+        default: ''
       job_filter:
         description: 'Select which job to run (leave empty or "all" to run all jobs)'
         required: false
         type: string
         default: 'all'
+      continue_on_error:
+        description: 'Continue on error (do not fail the workflow on test failures)'
+        required: false
+        type: boolean
+        default: true
+
+env:
+  AITER_COMMIT_OVERRIDE: ${{ inputs.aiter_ref }}
 
 concurrency:
   group: nightly-test-amd-${{ inputs.ref || github.ref }}
@@ -93,7 +116,7 @@ jobs:
         run: |
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-1-gpu --nightly --timeout-per-file 900 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-1-gpu --nightly --timeout-per-file 900 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -123,7 +146,7 @@ jobs:
           > 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 --nightly --timeout-per-file 7200 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -153,7 +176,7 @@ jobs:
           > 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-2-gpu-vlm --nightly --timeout-per-file 7200 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-2-gpu-vlm --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -184,7 +207,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-perf-text-2-gpu --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-perf-text-2-gpu --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -215,7 +238,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-perf-vlm-2-gpu --nightly --timeout-per-file 7200 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-perf-vlm-2-gpu --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -244,7 +267,7 @@ jobs:
         run: |
           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-gpt-oss --nightly --timeout-per-file 7200 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-gpt-oss --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -254,7 +277,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-grok1-fp8 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-grok1-fp8 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -286,7 +309,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-grok1-int4 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-grok1-int4 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -298,7 +321,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-grok1-int4 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-grok1-int4 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -329,7 +352,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-grok2 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-grok2 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -341,7 +364,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-grok2 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-grok2 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -372,7 +395,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-deepseek-v31 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-deepseek-v31 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -384,7 +407,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_ROCM700A=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-deepseek-v31 --nightly --timeout-per-file 18000 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-deepseek-v31 --nightly --timeout-per-file 18000 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -414,7 +437,7 @@ jobs:
           > 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-deepseek-v32 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-deepseek-v32 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -425,7 +448,7 @@ jobs:
           > 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-perf-8-gpu-deepseek-v32-basic --nightly --timeout-per-file 5400 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-deepseek-v32-basic --nightly --timeout-per-file 5400 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -455,7 +478,7 @@ jobs:
           > 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-deepseek-v32-mtp --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-deepseek-v32-mtp --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -466,7 +489,7 @@ jobs:
           > 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-perf-8-gpu-deepseek-v32-mtp --nightly --timeout-per-file 7200 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-deepseek-v32-mtp --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -496,7 +519,7 @@ jobs:
           > 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-kimi-k25 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-kimi-k25 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -525,7 +548,7 @@ jobs:
           > 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-8-gpu-qwen3-235b --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-8-gpu-qwen3-235b --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -557,7 +580,7 @@ jobs:
           > 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-glm5 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-glm5 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -588,7 +611,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-minimax-m25 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-minimax-m25 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -621,7 +644,7 @@ jobs:
         run: |
           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-1-gpu-mi35x --nightly --timeout-per-file 900 --continue-on-error || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-1-gpu-mi35x --nightly --timeout-per-file 900 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -653,7 +676,7 @@ jobs:
         run: |
           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-8-gpu-mi35x --nightly --timeout-per-file 7200 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -687,7 +710,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-grok1-int4 --nightly --timeout-per-file 5400 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-grok1-int4 --nightly --timeout-per-file 5400 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -699,7 +722,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-grok1-int4 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-grok1-int4 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -733,7 +756,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-grok2 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-grok2 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -745,7 +768,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e RCCL_MSCCL_ENABLE=0 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-grok2 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-grok2 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -778,7 +801,7 @@ jobs:
           > 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-8-gpu-mi35x-deepseek-r1-mxfp4 --nightly --timeout-per-file 7200 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-deepseek-r1-mxfp4 --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -822,7 +845,7 @@ jobs:
           > 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-8-gpu-mi35x-deepseek-v32 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-deepseek-v32 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -855,7 +878,7 @@ jobs:
           > 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-deepseek-v32-mtp --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-deepseek-v32-mtp --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -888,7 +911,7 @@ jobs:
           > 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-perf-8-gpu-mi35x-deepseek-v32-basic --nightly --timeout-per-file 5400 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-deepseek-v32-basic --nightly --timeout-per-file 5400 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -921,7 +944,7 @@ jobs:
           > 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-kimi-k25 --nightly --timeout-per-file 7200 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-kimi-k25 --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -954,7 +977,7 @@ jobs:
           > 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-8-gpu-mi35x-qwen3-235b-mxfp4 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-8-gpu-mi35x-qwen3-235b-mxfp4 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -988,7 +1011,7 @@ jobs:
           > 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-8-gpu-mi35x-glm5 --nightly --timeout-per-file 7200 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-glm5 --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -1021,7 +1044,7 @@ jobs:
           bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
             -e SGLANG_USE_AITER=1 \
             -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
-            python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-minimax-m25 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-minimax-m25 --nightly --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
@@ -1054,7 +1077,7 @@ jobs:
           > 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-perf-8-gpu-mi35x-deepseek-v32-mtp --nightly --timeout-per-file 7200 || TEST_EXIT_CODE=$?
+            python3 run_suite.py --hw amd --suite nightly-perf-8-gpu-mi35x-deepseek-v32-mtp --nightly --timeout-per-file 7200 ${{ inputs.continue_on_error && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 

.github/workflows/pr-test-amd-rocm720.yml

@@ -37,6 +37,16 @@ on:
         required: false
         type: string
         default: ""
+      aiter_ref:
+        description: 'Override AITER commit (optional, leave empty to use Dockerfile default)'
+        required: false
+        type: string
+        default: ''
+      continue_on_error:
+        description: 'Continue on error (do not fail the workflow on test failures)'
+        required: false
+        type: boolean
+        default: true
   workflow_call:
     inputs:
       ref:
@@ -49,6 +59,19 @@ on:
         required: false
         type: boolean
         default: false
+      aiter_ref:
+        description: 'Override AITER commit (optional, leave empty to use Dockerfile default)'
+        required: false
+        type: string
+        default: ''
+      continue_on_error:
+        description: 'Continue on error (do not fail the workflow on test failures)'
+        required: false
+        type: boolean
+        default: true
+
+env:
+  AITER_COMMIT_OVERRIDE: ${{ inputs.aiter_ref }}
 
 concurrency:
   # Include pr_head_sha in group for /rerun-stage dispatches to avoid collisions with main branch runs
@@ -146,8 +169,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+          bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Run test
         timeout-minutes: 14
         run: |
@@ -193,8 +215,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+          bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Run test
         timeout-minutes: 20
         run: |
@@ -236,12 +257,11 @@ jobs:
 
       - name: Install dependencies
         run: |
-          bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+          bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Run test
         timeout-minutes: 10
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-amd --continue-on-error
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-amd ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   jit-kernel-unit-test-amd:
     needs: [check-changes]
@@ -275,8 +295,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+          bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Run JIT kernel unit tests
         timeout-minutes: 10
         run: |
@@ -315,12 +334,11 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Run test
         timeout-minutes: 30
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 13 --timeout-per-file 1800 --continue-on-error
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 13 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   stage-b-test-small-1-gpu-amd-nondeterministic:
     needs: [check-changes]
@@ -354,12 +372,11 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Run test
         timeout-minutes: 30
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-nondeterministic --timeout-per-file 1800 --continue-on-error
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-nondeterministic --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   stage-b-test-small-1-gpu-amd-mi35x:
     needs: [check-changes]
@@ -393,12 +410,11 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Run test
         timeout-minutes: 30
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-mi35x --continue-on-error
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-mi35x ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   stage-b-test-large-1-gpu-amd:
     needs: [check-changes]
@@ -433,12 +449,11 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Run test
         timeout-minutes: 30
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 --continue-on-error
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   stage-b-test-large-2-gpu-amd:
     needs: [check-changes]
@@ -473,12 +488,11 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Run test
         timeout-minutes: 30
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 --continue-on-error
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   multimodal-gen-test-1-gpu-amd:
     needs: [check-changes]
@@ -523,7 +537,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build diffusion
+          bash scripts/ci/amd/amd_ci_install_dependency.sh diffusion
           docker exec ci_sglang pip install amdsmi
 
       - name: Setup kernel caches
@@ -653,7 +667,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build diffusion
+          bash scripts/ci/amd/amd_ci_install_dependency.sh diffusion
           docker exec ci_sglang pip install amdsmi
 
       - name: Setup kernel caches
@@ -774,8 +788,7 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Test RCCL multi-GPU communication
         timeout-minutes: 5
         run: |
@@ -785,7 +798,7 @@ jobs:
       - name: Run test
         timeout-minutes: 60
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 3600 --continue-on-error
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   stage-c-test-large-8-gpu-amd-mi35x:
     needs: [check-changes]
@@ -820,12 +833,11 @@ jobs:
           GITHUB_WORKSPACE: ${{ github.workspace }}
 
       - name: Install dependencies
-        run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh
-
       - name: Run test
         timeout-minutes: 60
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 1 --timeout-per-file 3600 --continue-on-error
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 1 --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   pr-test-amd-finish:
     needs:

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

@@ -34,6 +34,16 @@ on:
         required: false
         type: string
         default: ""
+      aiter_ref:
+        description: 'Override AITER commit (optional, leave empty to use Dockerfile default)'
+        required: false
+        type: string
+        default: ''
+      continue_on_error:
+        description: 'Continue on error (do not fail the workflow on test failures)'
+        required: false
+        type: boolean
+        default: false
   workflow_call:
     inputs:
       ref:
@@ -46,6 +56,19 @@ on:
         required: false
         type: boolean
         default: false
+      aiter_ref:
+        description: 'Override AITER commit (optional, leave empty to use Dockerfile default)'
+        required: false
+        type: string
+        default: ''
+      continue_on_error:
+        description: 'Continue on error (do not fail the workflow on test failures)'
+        required: false
+        type: boolean
+        default: false
+
+env:
+  AITER_COMMIT_OVERRIDE: ${{ inputs.aiter_ref }}
 
 concurrency:
   # Include pr_head_sha in group for /rerun-stage dispatches to avoid collisions with main branch runs
@@ -238,7 +261,7 @@ jobs:
       - name: Run test
         timeout-minutes: 10
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-amd
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-amd ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   jit-kernel-unit-test-amd:
     needs: [check-changes]
@@ -317,7 +340,7 @@ jobs:
       - name: Run test
         timeout-minutes: 30
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 14 --timeout-per-file 1800
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 14 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   stage-b-test-small-1-gpu-amd-nondeterministic:
     needs: [check-changes, stage-a-test-1-amd]
@@ -356,7 +379,7 @@ jobs:
       - name: Run test
         timeout-minutes: 30
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-nondeterministic --timeout-per-file 1800 --continue-on-error
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-nondeterministic --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   stage-b-test-small-1-gpu-amd-mi35x:
     needs: [check-changes, stage-a-test-1-amd]
@@ -395,7 +418,7 @@ jobs:
       - name: Run test
         timeout-minutes: 30
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-mi35x
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-mi35x ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   stage-b-test-large-1-gpu-amd:
     needs: [check-changes, stage-a-test-1-amd]
@@ -435,7 +458,7 @@ jobs:
       - name: Run test
         timeout-minutes: 30
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   stage-b-test-large-2-gpu-amd:
     needs: [check-changes, stage-a-test-1-amd]
@@ -475,7 +498,7 @@ jobs:
       - name: Run test
         timeout-minutes: 30
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   multimodal-gen-test-1-gpu-amd:
     needs: [check-changes]
@@ -762,7 +785,7 @@ jobs:
       - name: Run test
         timeout-minutes: 60
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 3600
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   stage-c-test-large-8-gpu-amd-mi35x:
     needs: [check-changes, call-gate, stage-b-test-small-1-gpu-amd, stage-b-test-large-2-gpu-amd]
@@ -802,7 +825,7 @@ jobs:
       - name: Run test
         timeout-minutes: 60
         run: |
-          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 1 --timeout-per-file 3600
+          bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 1 --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   # =============================================== Disaggregation ====================================================
   stage-b-test-large-8-gpu-35x-disaggregation-amd:
@@ -914,7 +937,7 @@ jobs:
         run: |
           bash scripts/ci/amd/amd_ci_exec.sh \
             -e SGLANG_TEST_RDMA_DEVICE="${{ env.SGLANG_TEST_RDMA_DEVICE }}" \
-            -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-8-gpu-35x-disaggregation-amd --timeout-per-file 1800
+            -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-8-gpu-35x-disaggregation-amd --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
 
   pr-test-amd-finish:
     needs:

.github/workflows/scheduled-aiter-latest-full-test.yml

@@ -0,0 +1,159 @@
+name: Scheduled Full AMD Test (AITER Latest)
+
+on:
+  schedule:
+    - cron: '0 20 * * 1'   # Monday 20:00 UTC
+    - cron: '0 20 * * 4'   # Thursday 20:00 UTC
+  workflow_dispatch:
+    inputs:
+      aiter_ref:
+        description: 'AITER git ref (branch, tag, or SHA). Default: main (latest commit)'
+        required: false
+        type: string
+        default: 'main'
+      job_filter:
+        description: 'Comma-separated workflows to run: nightly-amd, nightly-amd-rocm720, pr-test-amd, pr-test-amd-rocm720. Default: all'
+        required: false
+        type: string
+        default: 'all'
+      continue_on_error:
+        description: 'Continue running other workflows even if one fails'
+        required: false
+        type: boolean
+        default: true
+
+concurrency:
+  group: scheduled-aiter-latest-full-test-${{ github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  resolve-aiter:
+    runs-on: ubuntu-latest
+    outputs:
+      aiter_sha: ${{ steps.resolve.outputs.sha }}
+      run_nightly_amd: ${{ steps.parse.outputs.run_nightly_amd }}
+      run_nightly_amd_rocm720: ${{ steps.parse.outputs.run_nightly_amd_rocm720 }}
+      run_pr_test_amd: ${{ steps.parse.outputs.run_pr_test_amd }}
+      run_pr_test_amd_rocm720: ${{ steps.parse.outputs.run_pr_test_amd_rocm720 }}
+    steps:
+      - name: Resolve AITER commit
+        id: resolve
+        run: |
+          REF="${{ inputs.aiter_ref || 'main' }}"
+          echo "Resolving AITER ref: ${REF}"
+
+          SHA=$(git ls-remote https://github.com/ROCm/aiter.git "${REF}" | head -1 | cut -f1)
+          if [ -z "$SHA" ]; then
+            SHA=$(git ls-remote https://github.com/ROCm/aiter.git "refs/heads/${REF}" | head -1 | cut -f1)
+          fi
+          if [ -z "$SHA" ]; then
+            SHA=$(git ls-remote https://github.com/ROCm/aiter.git "refs/tags/${REF}" | head -1 | cut -f1)
+          fi
+          if [ -z "$SHA" ]; then
+            SHA="${REF}"
+          fi
+
+          echo "sha=${SHA}" >> $GITHUB_OUTPUT
+          echo "### AITER Ref Resolution" >> $GITHUB_STEP_SUMMARY
+          echo "- **Requested ref:** \`${REF}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- **Resolved SHA:** \`${SHA}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- **AITER commit:** https://github.com/ROCm/aiter/commit/${SHA}" >> $GITHUB_STEP_SUMMARY
+
+      - name: Parse job filter
+        id: parse
+        run: |
+          FILTER="${{ inputs.job_filter || 'all' }}"
+          echo "Job filter: ${FILTER}"
+
+          if [[ "$FILTER" == "all" ]]; then
+            echo "run_nightly_amd=true" >> $GITHUB_OUTPUT
+            echo "run_nightly_amd_rocm720=true" >> $GITHUB_OUTPUT
+            echo "run_pr_test_amd=true" >> $GITHUB_OUTPUT
+            echo "run_pr_test_amd_rocm720=true" >> $GITHUB_OUTPUT
+          else
+            # Wrap with commas for exact substring matching (avoids "nightly-amd" matching "nightly-amd-rocm720")
+            PADDED=",${FILTER// /},"
+            echo "run_nightly_amd=$(echo "$PADDED" | grep -q ',nightly-amd,' && echo true || echo false)" >> $GITHUB_OUTPUT
+            echo "run_nightly_amd_rocm720=$(echo "$PADDED" | grep -q ',nightly-amd-rocm720,' && echo true || echo false)" >> $GITHUB_OUTPUT
+            echo "run_pr_test_amd=$(echo "$PADDED" | grep -q ',pr-test-amd,' && echo true || echo false)" >> $GITHUB_OUTPUT
+            echo "run_pr_test_amd_rocm720=$(echo "$PADDED" | grep -q ',pr-test-amd-rocm720,' && echo true || echo false)" >> $GITHUB_OUTPUT
+          fi
+
+          echo "### Job Filter" >> $GITHUB_STEP_SUMMARY
+          echo "- **Filter:** \`${FILTER}\`" >> $GITHUB_STEP_SUMMARY
+
+  call-nightly-amd:
+    if: needs.resolve-aiter.outputs.run_nightly_amd == 'true'
+    needs: resolve-aiter
+    uses: ./.github/workflows/nightly-test-amd.yml
+    secrets: inherit
+    with:
+      aiter_ref: ${{ needs.resolve-aiter.outputs.aiter_sha }}
+      job_filter: 'all'
+      continue_on_error: ${{ inputs.continue_on_error == '' && true || inputs.continue_on_error }}
+
+  call-nightly-amd-rocm720:
+    if: needs.resolve-aiter.outputs.run_nightly_amd_rocm720 == 'true'
+    needs: resolve-aiter
+    uses: ./.github/workflows/nightly-test-amd-rocm720.yml
+    secrets: inherit
+    with:
+      aiter_ref: ${{ needs.resolve-aiter.outputs.aiter_sha }}
+      job_filter: 'all'
+      continue_on_error: ${{ inputs.continue_on_error == '' && true || inputs.continue_on_error }}
+
+  call-pr-test-amd:
+    if: needs.resolve-aiter.outputs.run_pr_test_amd == 'true'
+    needs: resolve-aiter
+    uses: ./.github/workflows/pr-test-amd.yml
+    secrets: inherit
+    with:
+      run_all_tests: true
+      aiter_ref: ${{ needs.resolve-aiter.outputs.aiter_sha }}
+      continue_on_error: ${{ inputs.continue_on_error == '' && true || inputs.continue_on_error }}
+
+  call-pr-test-amd-rocm720:
+    if: needs.resolve-aiter.outputs.run_pr_test_amd_rocm720 == 'true'
+    needs: resolve-aiter
+    uses: ./.github/workflows/pr-test-amd-rocm720.yml
+    secrets: inherit
+    with:
+      run_all_tests: true
+      aiter_ref: ${{ needs.resolve-aiter.outputs.aiter_sha }}
+      continue_on_error: ${{ inputs.continue_on_error == '' && true || inputs.continue_on_error }}
+
+  check-all-jobs:
+    if: always()
+    needs:
+      - resolve-aiter
+      - call-nightly-amd
+      - call-nightly-amd-rocm720
+      - call-pr-test-amd
+      - call-pr-test-amd-rocm720
+    runs-on: ubuntu-latest
+    steps:
+      - name: Summary
+        run: |
+          echo "## Scheduled Full AMD Test (AITER Latest) Results" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "- **AITER SHA:** \`${{ needs.resolve-aiter.outputs.aiter_sha }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- **AITER commit:** https://github.com/ROCm/aiter/commit/${{ needs.resolve-aiter.outputs.aiter_sha }}" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "| Workflow | Result |" >> $GITHUB_STEP_SUMMARY
+          echo "|----------|--------|" >> $GITHUB_STEP_SUMMARY
+          echo "| Nightly AMD (AITER Latest) | \`${{ needs.call-nightly-amd.result }}\` |" >> $GITHUB_STEP_SUMMARY
+          echo "| Nightly AMD ROCm 7.2 | \`${{ needs.call-nightly-amd-rocm720.result }}\` |" >> $GITHUB_STEP_SUMMARY
+          echo "| PR Test AMD (AITER Latest) | \`${{ needs.call-pr-test-amd.result }}\` |" >> $GITHUB_STEP_SUMMARY
+          echo "| PR Test AMD ROCm 7.2 | \`${{ needs.call-pr-test-amd-rocm720.result }}\` |" >> $GITHUB_STEP_SUMMARY
+
+      - name: Check if any job failed
+        run: |
+          if [[ "${{ contains(needs.*.result, 'failure') }}" == "true" ]]; then
+            echo "One or more workflows failed"
+            exit 1
+          fi
+          if [[ "${{ contains(needs.*.result, 'cancelled') }}" == "true" ]]; then
+            echo "One or more workflows were cancelled"
+            exit 1
+          fi
+          echo "All workflows passed"

scripts/ci/amd/amd_ci_install_dependency.sh

@@ -230,7 +230,11 @@ echo "[CI-AITER-CHECK] AITER version inside CI image: ${IMAGE_AITER_VERSION}"
 #############################################
 NEED_REBUILD="false"
 
-if [[ "${IMAGE_AITER_VERSION}" == "vnone" || "${IMAGE_AITER_VERSION}" == "v" ]]; then
+if [[ -n "${AITER_COMMIT_OVERRIDE:-}" ]]; then
+    echo "[CI-AITER-CHECK] AITER_COMMIT_OVERRIDE=${AITER_COMMIT_OVERRIDE} → forcing rebuild"
+    REPO_AITER_COMMIT="${AITER_COMMIT_OVERRIDE}"
+    NEED_REBUILD="true"
+elif [[ "${IMAGE_AITER_VERSION}" == "vnone" || "${IMAGE_AITER_VERSION}" == "v" ]]; then
     echo "[CI-AITER-CHECK] No AITER found in image → rebuild needed"
     NEED_REBUILD="true"
 elif [[ "${IMAGE_AITER_VERSION}" == "${REPO_AITER_COMMIT}" ]]; then
@@ -274,6 +278,24 @@ if [[ "${NEED_REBUILD}" == "true" ]]; then
     fi
     echo "[CI-AITER-CHECK] GPU_ARCH_LIST=${GPU_ARCH_LIST}"
 
+    # Re-apply Dockerfile hotpatches for ROCm 7.2 (the fresh clone lost them, can be removed after triton fixed this problem)
+    ROCM_VERSION=$(docker exec ci_sglang bash -c "cat /opt/rocm/.info/version 2>/dev/null || echo unknown")
+    if [[ "${ROCM_VERSION}" == 7.2* ]]; then
+        echo "[CI-AITER-CHECK] ROCm 7.2 detected (${ROCM_VERSION}), applying AITER hotpatches..."
+        docker exec ci_sglang bash -c "
+            cd /sgl-workspace/aiter && \
+            TARGET_FILE='aiter/ops/triton/attention/pa_mqa_logits.py' && \
+            if [ -f \"\${TARGET_FILE}\" ]; then \
+                sed -i '459 s/if.*:/if False:/' \"\${TARGET_FILE}\" && \
+                echo '[CI-AITER-CHECK] Hotpatch applied to pa_mqa_logits.py'; \
+            else \
+                echo '[CI-AITER-CHECK] pa_mqa_logits.py not found, skipping hotpatch'; \
+            fi
+        "
+    else
+        echo "[CI-AITER-CHECK] ROCm version=${ROCM_VERSION}, no hotpatch needed"
+    fi
+
     # build AITER
     docker exec ci_sglang bash -c "
         cd /sgl-workspace/aiter && \