[CI] Add quantization (#9832)

* add quantization to nightly CI.

* prep.

* fix lib name.

* remove deps that are not needed.

* fix slice.

.github/workflows/nightly_tests.yml

@@ -347,6 +347,64 @@ jobs:
         pip install slack_sdk tabulate
         python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
 
+  run_nightly_quantization_tests:
+    name: Torch quantization nightly tests
+    strategy:
+      fail-fast: false
+      max-parallel: 2
+      matrix: 
+        config:
+          - backend: "bitsandbytes"
+            test_location: "bnb"
+    runs-on:
+      group: aws-g6e-xlarge-plus
+    container:
+      image: diffusers/diffusers-pytorch-cuda
+      options: --shm-size "20gb" --ipc host --gpus 0
+    steps:
+      - name: Checkout diffusers
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+      - name: NVIDIA-SMI
+        run: nvidia-smi
+      - name: Install dependencies
+        run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+          python -m uv pip install -U ${{ matrix.config.backend }}
+          python -m uv pip install pytest-reportlog
+      - name: Environment
+        run: |
+          python utils/print_env.py
+      - name: ${{ matrix.config.backend }} quantization tests on GPU
+        env:
+          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
+          CUBLAS_WORKSPACE_CONFIG: :16:8
+          BIG_GPU_MEMORY: 40
+        run: |
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+            --make-reports=tests_${{ matrix.config.backend }}_torch_cuda \
+            --report-log=tests_${{ matrix.config.backend }}_torch_cuda.log \
+            tests/quantization/${{ matrix.config.test_location }}
+      - name: Failure short reports
+        if: ${{ failure() }}
+        run: |
+          cat reports/tests_${{ matrix.config.backend }}_torch_cuda_stats.txt
+          cat reports/tests_${{ matrix.config.backend }}_torch_cuda_failures_short.txt
+      - name: Test suite reports artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: torch_cuda_${{ matrix.config.backend }}_reports
+          path: reports
+      - name: Generate Report and Notify Channel
+        if: always()
+        run: |
+          pip install slack_sdk tabulate
+          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+
 # M1 runner currently not well supported
 # TODO: (Dhruv) add these back when we setup better testing for Apple Silicon
 #  run_nightly_tests_apple_m1:

tests/quantization/bnb/test_4bit.py

@@ -432,7 +432,6 @@ class SlowBnb4BitTests(Base4bitTests):
         expected_slice = np.array([0.1123, 0.1296, 0.1609, 0.1042, 0.1230, 0.1274, 0.0928, 0.1165, 0.1216])
 
         max_diff = numpy_cosine_similarity_distance(expected_slice, out_slice)
-        print(f"{max_diff=}")
         self.assertTrue(max_diff < 1e-2)
 
     def test_generate_quality_dequantize(self):

tests/quantization/bnb/test_mixed_int8.py

@@ -369,7 +369,7 @@ class SlowBnb8bitTests(Base8bitTests):
             output_type="np",
         ).images
         out_slice = output[0, -3:, -3:, -1].flatten()
-        expected_slice = np.array([0.0149, 0.0322, 0.0073, 0.0134, 0.0332, 0.011, 0.002, 0.0232, 0.0193])
+        expected_slice = np.array([0.0376, 0.0359, 0.0015, 0.0449, 0.0479, 0.0098, 0.0083, 0.0295, 0.0295])
 
         max_diff = numpy_cosine_similarity_distance(expected_slice, out_slice)
         self.assertTrue(max_diff < 1e-2)