[AMD] [GLM-5 Day 0] Add GLM-5 nightly test (#18911)

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

@@ -32,6 +32,7 @@ on:
           - 'nightly-8-gpu-deepseek-v32-rocm720'
           - 'nightly-8-gpu-deepseek-v32-mtp-rocm720'
           - 'nightly-8-gpu-kimi-k25-rocm720'
+          - 'nightly-8-gpu-glm5-rocm720'
           # MI35x ROCm 7.2 jobs
           - 'nightly-test-1-gpu-mi35x-rocm720'
           - 'nightly-accuracy-8-gpu-mi35x-rocm720'
@@ -43,6 +44,7 @@ on:
           - 'nightly-perf-8-gpu-mi35x-deepseek-v32-basic-rocm720'
           - 'nightly-perf-8-gpu-mi35x-deepseek-v32-mtp-rocm720'
           - 'nightly-8-gpu-mi35x-kimi-k25-rocm720'
+          - 'nightly-8-gpu-mi35x-glm5-rocm720'
   workflow_call:
     inputs:
       ref:
@@ -494,6 +496,39 @@ jobs:
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
+  # 8-GPU GLM-5 (Accuracy) ROCm 7.2
+  nightly-8-gpu-glm5-rocm720:
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-glm5-rocm720')
+    runs-on: linux-mi325-gpu-8
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Setup docker (ROCm 7.2)
+        run: |
+          touch github_summary.md
+          bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
+        env:
+          GITHUB_WORKSPACE: ${{ github.workspace }}
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
+          # GLM-5 requires latest transformers for glm_moe_dsa architecture
+          bash scripts/ci/amd/amd_ci_exec.sh pip install git+https://github.com/huggingface/transformers.git
+
+      - name: Accuracy Test ROCm 7.2 (8-GPU GLM-5 NSA)
+        timeout-minutes: 120
+        run: |
+          > github_summary.md  # Clear summary file
+          bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-glm5 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
+          echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
+          exit ${TEST_EXIT_CODE:-0}
+
   # ============================================== MI35x ROCm 7.2 Tests ==============================================
   # MI35x 1-GPU ROCm 7.2 tests
   nightly-test-1-gpu-mi35x-rocm720:
@@ -825,6 +860,40 @@ jobs:
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
+  nightly-8-gpu-mi35x-glm5-rocm720:
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-mi35x-glm5-rocm720')
+    runs-on: linux-mi35x-gpu-8
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Setup docker (ROCm 7.2)
+        run: |
+          touch github_summary.md
+          bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
+        env:
+          GITHUB_WORKSPACE: ${{ github.workspace }}
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
+          # Install tabulate for run_suite.py (missing in MI35x container)
+          bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
+          # GLM-5 requires latest transformers for glm_moe_dsa architecture
+          bash scripts/ci/amd/amd_ci_exec.sh pip install git+https://github.com/huggingface/transformers.git
+
+      - name: Accuracy Test MI35x ROCm 7.2 (8-GPU GLM-5 NSA)
+        timeout-minutes: 180
+        run: |
+          > github_summary.md  # Clear summary file
+          bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
+            python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-glm5 --nightly --timeout-per-file 7200 --continue-on-error || TEST_EXIT_CODE=$?
+          echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
+          exit ${TEST_EXIT_CODE:-0}
+
   # MI35x 8-GPU DeepSeek-V3.2 Performance Test (MTP) ROCm 7.2
   nightly-perf-8-gpu-mi35x-deepseek-v32-mtp-rocm720:
     if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-perf-8-gpu-mi35x-deepseek-v32-mtp-rocm720')
@@ -877,6 +946,7 @@ jobs:
       - nightly-8-gpu-deepseek-v32-rocm720
       - nightly-8-gpu-deepseek-v32-mtp-rocm720
       - nightly-8-gpu-kimi-k25-rocm720
+      - nightly-8-gpu-glm5-rocm720
       # MI35x ROCm 7.2 jobs
       - nightly-test-1-gpu-mi35x-rocm720
       - nightly-accuracy-8-gpu-mi35x-rocm720
@@ -888,6 +958,7 @@ jobs:
       - nightly-perf-8-gpu-mi35x-deepseek-v32-basic-rocm720
       - nightly-perf-8-gpu-mi35x-deepseek-v32-mtp-rocm720
       - nightly-8-gpu-mi35x-kimi-k25-rocm720
+      - nightly-8-gpu-mi35x-glm5-rocm720
     runs-on: ubuntu-latest
     steps:
       - name: Check if any job failed

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

@@ -32,9 +32,11 @@ on:
           - 'nightly-8-gpu-deepseek-v32'
           - 'nightly-8-gpu-deepseek-v32-mtp'
           - 'nightly-8-gpu-kimi-k25'
+          - 'nightly-8-gpu-glm5'
           # MI35x jobs
           - 'nightly-test-1-gpu-mi35x'
           - 'nightly-8-gpu-mi35x-kimi-k25'
+          - 'nightly-8-gpu-mi35x-glm5'
           - 'nightly-accuracy-8-gpu-mi35x'
           - 'nightly-8-gpu-mi35x-grok1-int4'
           - 'nightly-8-gpu-mi35x-grok2'
@@ -494,6 +496,38 @@ jobs:
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
+  nightly-8-gpu-glm5:
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-glm5')
+    runs-on: linux-mi325-gpu-8
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Setup docker
+        run: |
+          touch github_summary.md
+          bash scripts/ci/amd/amd_ci_start_container.sh
+        env:
+          GITHUB_WORKSPACE: ${{ github.workspace }}
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/amd/amd_ci_install_dependency.sh
+          # GLM-5 requires latest transformers for glm_moe_dsa architecture
+          bash scripts/ci/amd/amd_ci_exec.sh pip install git+https://github.com/huggingface/transformers.git
+
+      - name: Accuracy Test (8-GPU GLM-5 NSA)
+        timeout-minutes: 120
+        run: |
+          > github_summary.md  # Clear summary file
+          bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
+            python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-glm5 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
+          echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
+          exit ${TEST_EXIT_CODE:-0}
+
   # ============================================== MI35x Tests ==============================================
   # MI35x 1-GPU tests - platform-agnostic tests that may work on CDNA4 (gfx950)
   nightly-test-1-gpu-mi35x:
@@ -827,6 +861,40 @@ jobs:
           echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
           exit ${TEST_EXIT_CODE:-0}
 
+  nightly-8-gpu-mi35x-glm5:
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-mi35x-glm5')
+    runs-on: linux-mi35x-gpu-8
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Setup docker
+        run: |
+          touch github_summary.md
+          bash scripts/ci/amd/amd_ci_start_container.sh
+        env:
+          GITHUB_WORKSPACE: ${{ github.workspace }}
+
+      - name: Install dependencies
+        run: |
+          bash scripts/ci/amd/amd_ci_install_dependency.sh
+          # Install tabulate for run_suite.py (missing in MI35x container)
+          bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
+          # GLM-5 requires latest transformers for glm_moe_dsa architecture
+          bash scripts/ci/amd/amd_ci_exec.sh pip install git+https://github.com/huggingface/transformers.git
+
+      - name: Accuracy Test MI35x (8-GPU GLM-5 NSA)
+        timeout-minutes: 180
+        run: |
+          > github_summary.md  # Clear summary file
+          bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
+            -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
+            python3 run_suite.py --hw amd --suite nightly-amd-8-gpu-mi35x-glm5 --nightly --timeout-per-file 7200 || TEST_EXIT_CODE=$?
+          echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
+          exit ${TEST_EXIT_CODE:-0}
+
   # MI35x 8-GPU DeepSeek-V3.2 Performance Test (MTP)
   nightly-perf-8-gpu-mi35x-deepseek-v32-mtp:
     if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-perf-8-gpu-mi35x-deepseek-v32-mtp')
@@ -879,6 +947,7 @@ jobs:
       - nightly-8-gpu-deepseek-v32
       - nightly-8-gpu-deepseek-v32-mtp
       - nightly-8-gpu-kimi-k25
+      - nightly-8-gpu-glm5
       # MI35x jobs
       - nightly-test-1-gpu-mi35x
       - nightly-accuracy-8-gpu-mi35x
@@ -888,6 +957,7 @@ jobs:
       - nightly-accuracy-8-gpu-mi35x-deepseek-v32
       - nightly-accuracy-8-gpu-mi35x-deepseek-v32-mtp
       - nightly-8-gpu-mi35x-kimi-k25
+      - nightly-8-gpu-mi35x-glm5
       # MI35x perf jobs excluded from check - perf failures don't block CI
       # - nightly-perf-8-gpu-mi35x-deepseek-v32-basic
       # - nightly-perf-8-gpu-mi35x-deepseek-v32-mtp