From 547b886b3c1529e662a790c409dcb7f936c07d7a Mon Sep 17 00:00:00 2001
From: Alison Shao <54658187+alisonshao@users.noreply.github.com>
Date: Mon, 1 Jun 2026 23:40:48 -0700
Subject: [PATCH] ci: drop redundant multimodal-server jobs from nightly
 (Nvidia) (#26985)

---
 .github/workflows/nightly-test-nvidia.yml | 123 ----------------------
 1 file changed, 123 deletions(-)

diff --git a/.github/workflows/nightly-test-nvidia.yml b/.github/workflows/nightly-test-nvidia.yml
index f77dfba5c..29de8d888 100644
--- a/.github/workflows/nightly-test-nvidia.yml
+++ b/.github/workflows/nightly-test-nvidia.yml
@@ -21,8 +21,6 @@ on:
           - 'nightly-test-text-perf-2-gpu-h100'
           - 'nightly-test-vlm-accuracy-2-gpu-h100'
           - 'nightly-test-vlm-perf-2-gpu-h100'
-          - 'nightly-test-multimodal-server-1-gpu'
-          - 'nightly-test-multimodal-server-2-gpu'
           - 'nightly-test-perf-4-gpu-b200'
           - 'nightly-test-perf-8-gpu-b200'
           - 'nightly-test-specialized-8-gpu-b200'
@@ -487,123 +485,6 @@ jobs:
       - uses: ./.github/actions/upload-cuda-coredumps
         if: failure()
 
-  # diffusion performance tests
-  nightly-test-multimodal-server-1-gpu:
-    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-multimodal-server-1-gpu')
-    runs-on: 1-gpu-h100
-    strategy:
-      fail-fast: false
-      max-parallel: 2
-      matrix:
-        part: [0, 1]
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ inputs.ref || github.ref }}
-
-      - uses: ./.github/actions/check-maintenance
-
-      - name: Install dependencies
-        run: |
-          bash scripts/ci/cuda/ci_install_dependency.sh diffusion
-          pip install slack_sdk
-
-      - name: Run diffusion server tests
-        env:
-          SGLANG_DIFFUSION_SLACK_TOKEN: ${{ secrets.SGLANG_DIFFUSION_SLACK_TOKEN }}
-          GITHUB_RUN_ID: ${{ github.run_id }}
-          GPU_CONFIG: "1-gpu-h100"
-
-        timeout-minutes: 60
-        run: |
-          cd python
-          python3 sglang/multimodal_gen/test/run_suite.py \
-            --suite 1-gpu \
-            --partition-id ${{ matrix.part }} \
-            --total-partitions 2
-
-      - name: Collect diffusion performance metrics
-        if: always()
-        run: |
-          python3 scripts/ci/utils/diffusion/save_diffusion_metrics.py \
-            --gpu-config 1-gpu-h100 \
-            --run-id ${{ github.run_id }} \
-            --output python/diffusion-metrics-1gpu-partition-${{ matrix.part }}.json \
-            --results-json python/diffusion-results.json
-
-      - name: Upload diffusion metrics
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: diffusion-metrics-1gpu-partition-${{ matrix.part }}
-          path: python/diffusion-metrics-1gpu-partition-${{ matrix.part }}.json
-          retention-days: 90
-          if-no-files-found: ignore
-
-      - uses: ./.github/actions/upload-cuda-coredumps
-        if: failure()
-        with:
-          artifact-suffix: ${{ matrix.part }}
-
-  nightly-test-multimodal-server-2-gpu:
-    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-multimodal-server-2-gpu')
-    runs-on: 2-gpu-h100
-    strategy:
-      fail-fast: false
-      max-parallel: 2
-      matrix:
-        part: [0, 1]
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ inputs.ref || github.ref }}
-
-      - uses: ./.github/actions/check-maintenance
-
-      - name: Install dependencies
-        run: |
-          bash scripts/ci/cuda/ci_install_dependency.sh diffusion
-          pip install slack_sdk
-
-      - name: Run diffusion server tests
-        env:
-          SGLANG_DIFFUSION_SLACK_TOKEN: ${{ secrets.SGLANG_DIFFUSION_SLACK_TOKEN }}
-          GITHUB_RUN_ID: ${{ github.run_id }}
-          GPU_CONFIG: "2-gpu-h100"
-
-        timeout-minutes: 210
-        run: |
-          cd python
-          python3 sglang/multimodal_gen/test/run_suite.py \
-            --suite 2-gpu \
-            --partition-id ${{ matrix.part }} \
-            --total-partitions 2
-
-      - name: Collect diffusion performance metrics
-        if: always()
-        run: |
-          python3 scripts/ci/utils/diffusion/save_diffusion_metrics.py \
-            --gpu-config 2-gpu-h100 \
-            --run-id ${{ github.run_id }} \
-            --output python/diffusion-metrics-2gpu-partition-${{ matrix.part }}.json \
-            --results-json python/diffusion-results.json
-
-      - name: Upload diffusion metrics
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: diffusion-metrics-2gpu-partition-${{ matrix.part }}
-          path: python/diffusion-metrics-2gpu-partition-${{ matrix.part }}.json
-          retention-days: 90
-          if-no-files-found: ignore
-
-      - uses: ./.github/actions/upload-cuda-coredumps
-        if: failure()
-        with:
-          artifact-suffix: ${{ matrix.part }}
-
   # B200 Performance tests - 4 GPU
   nightly-test-perf-4-gpu-b200:
     if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-perf-4-gpu-b200')
@@ -728,8 +609,6 @@ jobs:
     needs:
       - nightly-test-general-8-gpu-h200
       - nightly-test-general-8-gpu-b200
-      - nightly-test-multimodal-server-1-gpu
-      - nightly-test-multimodal-server-2-gpu
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
@@ -779,8 +658,6 @@ jobs:
       - nightly-test-text-perf-2-gpu-h100
       - nightly-test-vlm-accuracy-2-gpu-h100
       - nightly-test-vlm-perf-2-gpu-h100
-      - nightly-test-multimodal-server-1-gpu
-      - nightly-test-multimodal-server-2-gpu
       - nightly-test-perf-4-gpu-b200
       - nightly-test-specialized-8-gpu-b200
       - nightly-test-diffusion-comparison