[benchmarks] overhaul benchmarks

.github/workflows/benchmark.yml

@@ -13,15 +13,15 @@ env:
   MKL_NUM_THREADS: 8
 
 jobs:
-  torch_pipelines_cuda_benchmark_tests:
+  torch_models_cuda_benchmark_tests:
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_BENCHMARK }}
-    name: Torch Core Pipelines CUDA Benchmarking Tests
+    name: Torch Core Models CUDA Benchmarking Tests
     strategy:
       fail-fast: false
       max-parallel: 1
     runs-on:
-      group: aws-g6-4xlarge-plus
+      group: aws-g6e-xlarge-plus
     container:
       image: diffusers/diffusers-pytorch-cuda
       options: --shm-size "16gb" --ipc host --gpus 0
@@ -37,8 +37,9 @@ jobs:
         run: |
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           python -m uv pip install -e [quality,test]
-          python -m uv pip install pandas peft
-          python -m uv pip uninstall transformers && python -m uv pip install transformers==4.48.0
+          python -m uv pip install pandas peft torchprofile
+          # Temporary.
+          pip install --force-reinstall https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-manylinux_2_24_x86_64.whl
       - name: Environment
         run: |
           python utils/print_env.py
@@ -47,8 +48,8 @@ jobs:
             HF_TOKEN: ${{ secrets.DIFFUSERS_BOT_TOKEN }}
             BASE_PATH: benchmark_outputs
         run: |
-          export TOTAL_GPU_MEMORY=$(python -c "import torch; print(torch.cuda.get_device_properties(0).total_memory / (1024**3))")
-          cd benchmarks && mkdir ${BASE_PATH} && python run_all.py && python push_results.py
+          cd benchmarks && python run_all.py && python push_results.py
+          mkdir ${BASE_PATH} && mv *.csv ${BASE_PATH}
 
       - name: Test suite reports artifacts
         if: ${{ always() }}