chore(ci/litjob): fix and optimize GPU related tests (#21290)

* fix: add unzip to dependencies in pytorch workflow
* fix: update variable interpolation for PACKAGE_NAME in YAML workflows
* fix: update variable interpolation for PACKAGE_NAME in fabric workflow
* fix: disable CUDA_LAUNCH_BLOCKING to speed up tests
* apply suggestion

Author: bhimrazy

.azure/gpu-tests-fabric.yml

@@ -76,7 +76,7 @@ jobs:
           cuda_ver=$(python -c "import torch ; print(''.join(map(str, torch.version.cuda.split('.')[:2])))")
           echo "##vso[task.setvariable variable=CUDA_VERSION_MM]$cuda_ver"
           echo "##vso[task.setvariable variable=TORCH_URL]https://download.pytorch.org/whl/cu${cuda_ver}/torch_stable.html"
-          scope=$(python -c 'n = "$(PACKAGE_NAME)" ; print(dict(fabric="lightning_fabric").get(n, n))')
+          scope=$(python -c 'n = "${PACKAGE_NAME}" ; print(dict(fabric="lightning_fabric").get(n, n))')
           echo "##vso[task.setvariable variable=COVERAGE_SOURCE]$scope"
         displayName: "set env. vars"
       - bash: |
@@ -140,7 +140,7 @@ jobs:
 
       - bash: |
           set -e
-          extra=$(python -c "print({'lightning': 'fabric-'}.get('$(PACKAGE_NAME)', ''))")
+          extra=$(python -c "print({'lightning': 'fabric-'}.get('${PACKAGE_NAME}', ''))")
           pip install -e ".[${extra}dev]" -U --upgrade-strategy=eager --extra-index-url="${TORCH_URL}"
         displayName: "Install package & dependencies"
 

.azure/gpu-tests-pytorch.yml

@@ -75,7 +75,7 @@ jobs:
           cuda_ver=$(python -c "import torch ; print(''.join(map(str, torch.version.cuda.split('.')[:2])))")
           echo "##vso[task.setvariable variable=CUDA_VERSION_MM]$cuda_ver"
           echo "##vso[task.setvariable variable=TORCH_URL]https://download.pytorch.org/whl/cu${cuda_ver}/torch_stable.html"
-          scope=$(python -c 'n = "$(PACKAGE_NAME)" ; print(dict(pytorch="pytorch_lightning").get(n, n))')
+          scope=$(python -c 'n = "${PACKAGE_NAME}" ; print(dict(pytorch="pytorch_lightning").get(n, n))')
           echo "##vso[task.setvariable variable=COVERAGE_SOURCE]$scope"
         displayName: "set env. vars"
       - bash: |
@@ -139,7 +139,7 @@ jobs:
 
       - bash: |
           set -e
-          extra=$(python -c "print({'lightning': 'pytorch-'}.get('$(PACKAGE_NAME)', ''))")
+          extra=$(python -c "print({'lightning': 'pytorch-'}.get('${PACKAGE_NAME}', ''))")
           pip install -e ".[${extra}dev]" -U --upgrade-strategy=eager --extra-index-url="${TORCH_URL}"
         displayName: "Install package & dependencies"
 

.lightning/workflows/fabric.yml

@@ -85,7 +85,7 @@ run: |
   CUDA_VERSION_M_M="${CUDA_VERSION%.*}"  # "12.6"
   CUDA_VERSION_MM="${CUDA_VERSION_M_M//./}"  # "126"
   export UV_TORCH_BACKEND=cu${CUDA_VERSION_MM}
-  COVERAGE_SOURCE=$(python -c 'n = "$(PACKAGE_NAME)" ; print(dict(fabric="lightning_fabric").get(n, n))')
+  COVERAGE_SOURCE=$(python -c 'n = "${PACKAGE_NAME}" ; print(dict(fabric="lightning_fabric").get(n, n))')
   echo "collecting coverage for: ${COVERAGE_SOURCE}"
 
   uv pip install fire wget packaging "lightning-utilities[cli]"
@@ -120,7 +120,7 @@ run: |
   fi
 
   echo "Install package with [${PACKAGE_NAME}] extras"
-  extra=$(python -c "print({'lightning': 'fabric-'}.get('$(PACKAGE_NAME)', ''))")
+  extra=$(python -c "print({'lightning': 'fabric-'}.get('${PACKAGE_NAME}', ''))")
   uv pip install ".[${extra}dev]" --upgrade
 
   python requirements/collect_env_details.py

.lightning/workflows/pytorch.yml

@@ -27,7 +27,6 @@ env:
   DEBIAN_FRONTEND: "noninteractive"
   CUDA_TOOLKIT_ROOT_DIR: "/usr/local/cuda"
   MKL_THREADING_LAYER: "GNU"
-  CUDA_LAUNCH_BLOCKING: "1"
   NCCL_DEBUG: "INFO"
   TORCHDYNAMO_VERBOSE: "1"
   FREEZE_REQUIREMENTS: "1"
@@ -50,7 +49,8 @@ run: |
         openmpi-bin \
         ninja-build \
         libnccl2 \
-        libnccl-dev
+        libnccl-dev \
+        unzip
 
   echo "Install Python ${python_version} and UV"
   apt-get install -y python${python_version} python${python_version}-venv python${python_version}-dev
@@ -85,7 +85,7 @@ run: |
   CUDA_VERSION_M_M="${CUDA_VERSION%.*}"  # "12.6"
   CUDA_VERSION_MM="${CUDA_VERSION_M_M//./}"  # "126"
   export UV_TORCH_BACKEND=cu${CUDA_VERSION_MM}
-  COVERAGE_SOURCE=$(python -c 'n = "$(PACKAGE_NAME)" ; print(dict(fabric="pytorch_lightning").get(n, n))')
+  COVERAGE_SOURCE=$(python -c 'n = "${PACKAGE_NAME}" ; print(dict(fabric="pytorch_lightning").get(n, n))')
   echo "collecting coverage for: ${COVERAGE_SOURCE}"
 
   uv pip install -q fire wget packaging "lightning-utilities[cli]"
@@ -120,7 +120,7 @@ run: |
   fi
 
   echo "Install package"
-  extra=$(python -c "print({'lightning': 'pytorch-'}.get('$(PACKAGE_NAME)', ''))")
+  extra=$(python -c "print({'lightning': 'pytorch-'}.get('${PACKAGE_NAME}', ''))")
   uv pip install -e ".[${extra}dev]" --upgrade
 
   echo "Ensure only a single package is installed"