simplify call_gpu_tests github action

.github/workflows/call_gpu_tests.yml

@@ -32,52 +32,37 @@ on:
         type: string
 
 jobs:
-  basic-tests-on-gpu:
+  gpu_tests:
     runs-on: ${{ inputs.os }}
     steps:
-      - name: checkout repo ${{ github.event_name == 'workflow_dispatch' && inputs.commit_id || github.sha }}
+      - name: Checkout repo at ${{ github.event_name == 'workflow_dispatch' && inputs.commit_id || github.sha }}
         uses: actions/checkout@v4
         with:
           ref: ${{ github.event_name == 'workflow_dispatch' && inputs.commit_id || github.sha }}
+      - name: Set up Python ${{ inputs.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ inputs.python-version }}
       - name: Install Rust
         shell: bash
         run: |
            curl https://sh.rustup.rs -sSf | sh -s -- -y --default-toolchain 1.75.0
            echo "$HOME/.cargo/bin" >> $GITHUB_PATH
-      - name: Set up Python ${{ inputs.python-version }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ inputs.python-version }}
-      - name: Show GPUs
+      - name: Install NVIDIA SDK
         run: |
           nvidia-smi
-      - name: Update Ubuntu
-        run: |
-          sudo apt-get update
-          sudo apt-get -y upgrade
-      - name: Ensure NVIDIA SDK available
-        run: |
-          sudo apt-get -y install cuda-toolkit-12.6
+          sudo apt-get --yes update
+          sudo apt-get --yes install cuda-toolkit-12.6
           echo "/usr/local/cuda-12.6/bin" >> $GITHUB_PATH
-      - name: Install dependencies
-        shell: bash
-        run: |
-          python -m pip install --upgrade pip
-          pip install pytest
-          pip install -e .[schemas,test,bench]
-          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-      - name: GPU pip installs
+      - name: Install guidance in ${{ inputs.os }}
         run: |
-          pip install sentencepiece
-          pip install accelerate
-          echo "=============================="
-          pip uninstall -y transformers
-          pip uninstall -y llama-cpp-python
-          CMAKE_ARGS="-DGGML_CUDA=on" pip install -e .[llamacpp,transformers]
+          pip install --upgrade pip
+          pip install sentencepiece accelerate
+          CMAKE_ARGS="-DGGML_CUDA=on" pip install -e .[llamacpp,transformers,test]
       - name: Check GPU available
         run: |
           python -c "import torch; assert torch.cuda.is_available()"
-      - name: Run tests (except server) for ${{ inputs.model }}
+      - name: gpu_tests for ${{ inputs.model }}
         run: |
           pytest -vv --cov=guidance --cov-report=xml --cov-report=term-missing \
             --selected_model ${{ inputs.model }} \