[diffusion] CI: temporarily disable accuracy ci (#22031)

.github/workflows/pr-test-multimodal-gen.yml

@@ -159,108 +159,6 @@ jobs:
         with:
           artifact-suffix: ${{ matrix.part }}
 
-  multimodal-gen-component-accuracy-1-gpu:
-    if: |
-      (inputs.target_stage == 'multimodal-gen-component-accuracy-1-gpu') ||
-      (
-        !inputs.target_stage &&
-        ((github.event_name == 'schedule' || inputs.test_parallel_dispatch == 'true') || (inputs.caller_needs_failure != 'true' && !cancelled())) &&
-        inputs.multimodal_gen == 'true'
-      )
-    runs-on: 1-gpu-h100
-    timeout-minutes: 240
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
-
-      - uses: ./.github/actions/check-stage-health
-
-      - uses: ./.github/actions/check-maintenance
-
-      - name: Download artifacts
-        if: inputs.sgl_kernel == 'true'
-        uses: actions/download-artifact@v4
-        with:
-          path: sgl-kernel/dist/
-          merge-multiple: true
-          pattern: wheel-python3.10-cuda12.9
-
-      - name: Install dependencies
-        timeout-minutes: 20
-        run: |
-          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh diffusion
-
-      - name: Run diffusion component accuracy tests (1-GPU)
-        timeout-minutes: 240
-        env:
-          RUNAI_STREAMER_MEMORY_LIMIT: 0
-        run: |
-          cd python
-          if [ "${{ inputs.continue_on_error }}" = "true" ]; then
-            exit_code=0
-            python3 -m pytest -s -v sglang/multimodal_gen/test/server/test_accuracy_1_gpu_a.py || exit_code=$?
-            python3 -m pytest -s -v sglang/multimodal_gen/test/server/test_accuracy_1_gpu_b.py || exit_code=$?
-            exit $exit_code
-          fi
-          python3 -m pytest -s -v sglang/multimodal_gen/test/server/test_accuracy_1_gpu_a.py
-          python3 -m pytest -s -v sglang/multimodal_gen/test/server/test_accuracy_1_gpu_b.py
-
-      - uses: ./.github/actions/upload-cuda-coredumps
-        if: always()
-
-  multimodal-gen-component-accuracy-2-gpu:
-    if: |
-      (inputs.target_stage == 'multimodal-gen-component-accuracy-2-gpu') ||
-      (
-        !inputs.target_stage &&
-        ((github.event_name == 'schedule' || inputs.test_parallel_dispatch == 'true') || (inputs.caller_needs_failure != 'true' && !cancelled())) &&
-        inputs.multimodal_gen == 'true'
-      )
-    runs-on: 2-gpu-h100
-    timeout-minutes: 240
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
-
-      - uses: ./.github/actions/check-stage-health
-
-      - uses: ./.github/actions/check-maintenance
-
-      - name: Download artifacts
-        if: inputs.sgl_kernel == 'true'
-        uses: actions/download-artifact@v4
-        with:
-          path: sgl-kernel/dist/
-          merge-multiple: true
-          pattern: wheel-python3.10-cuda12.9
-
-      - name: Install dependencies
-        timeout-minutes: 20
-        run: |
-          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh diffusion
-
-      - name: Run diffusion component accuracy tests (2-GPU)
-        timeout-minutes: 240
-        env:
-          RUNAI_STREAMER_MEMORY_LIMIT: 0
-        run: |
-          cd python
-          if [ "${{ inputs.continue_on_error }}" = "true" ]; then
-            exit_code=0
-            torchrun --nproc_per_node=2 -m pytest -s -v sglang/multimodal_gen/test/server/test_accuracy_2_gpu_a.py || exit_code=$?
-            torchrun --nproc_per_node=2 -m pytest -s -v sglang/multimodal_gen/test/server/test_accuracy_2_gpu_b.py || exit_code=$?
-            exit $exit_code
-          fi
-          torchrun --nproc_per_node=2 -m pytest -s -v sglang/multimodal_gen/test/server/test_accuracy_2_gpu_a.py
-          torchrun --nproc_per_node=2 -m pytest -s -v sglang/multimodal_gen/test/server/test_accuracy_2_gpu_b.py
-
-      - uses: ./.github/actions/upload-cuda-coredumps
-        if: always()
-
   multimodal-gen-test-1-b200:
     if: |
       (inputs.target_stage == 'multimodal-gen-test-1-b200') ||

.github/workflows/pr-test.yml

@@ -890,8 +890,6 @@ jobs:
       (
         inputs.target_stage == 'multimodal-gen-test-1-gpu' ||
         inputs.target_stage == 'multimodal-gen-test-2-gpu' ||
-        inputs.target_stage == 'multimodal-gen-component-accuracy-1-gpu' ||
-        inputs.target_stage == 'multimodal-gen-component-accuracy-2-gpu' ||
         inputs.target_stage == 'multimodal-gen-test-1-b200' ||
         inputs.target_stage == 'multimodal-gen-unit-test' ||
         (

scripts/ci/utils/slash_command_handler.py

@@ -271,8 +271,6 @@ def handle_rerun_stage(
         "stage-c-test-deepep-8-gpu-h200",
         "multimodal-gen-test-1-gpu",
         "multimodal-gen-test-2-gpu",
-        "multimodal-gen-component-accuracy-1-gpu",
-        "multimodal-gen-component-accuracy-2-gpu",
         "multimodal-gen-test-1-b200",
     ]