Update CI setup (#13291)

* drop mamba
* use legacy GPU machines

.azure-pipelines/gpu-benchmark.yml

@@ -26,7 +26,7 @@ jobs:
   - job: benchmarks
     timeoutInMinutes: "90"
     cancelTimeoutInMinutes: "2"
-    pool: azure-gpus-spot
+    pool: azure-jirka-spot
     container:
       image: "pytorchlightning/pytorch_lightning:base-cuda-py3.9-torch1.11"
       options: "--runtime=nvidia -e NVIDIA_VISIBLE_DEVICES=all --shm-size=32g"

.azure-pipelines/gpu-tests.yml

@@ -29,7 +29,7 @@ jobs:
     # how much time to give 'run always even if cancelled tasks' before stopping them
     cancelTimeoutInMinutes: "2"
 
-    pool: azure-gpus-spot
+    pool: azure-jirka-spot
 
     container:
       image: $(image)

.github/workflows/ci_dockers.yml

@@ -97,7 +97,7 @@ jobs:
             UBUNTU_VERSION=${{ matrix.ubuntu_version }}
           file: dockers/base-cuda/Dockerfile
           push: false
-        timeout-minutes: 75
+        timeout-minutes: 95
 
   build-Conda:
     runs-on: ubuntu-20.04
@@ -123,7 +123,7 @@ jobs:
             CUDA_VERSION=${{ matrix.cuda_version }}
           file: dockers/base-conda/Dockerfile
           push: false
-        timeout-minutes: 75
+        timeout-minutes: 95
 
   build-ipu:
     runs-on: ubuntu-20.04

.github/workflows/events-nightly.yml

@@ -146,7 +146,7 @@ jobs:
           file: dockers/base-cuda/Dockerfile
           push: ${{ env.PUSH_TO_HUB }}
           tags: pytorchlightning/pytorch_lightning:base-cuda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }}
-        timeout-minutes: 85
+        timeout-minutes: 95
 
       # report failure to Slack
       - name: Slack notification
@@ -197,7 +197,7 @@ jobs:
           file: dockers/base-conda/Dockerfile
           push: ${{ env.PUSH_TO_HUB }}
           tags: pytorchlightning/pytorch_lightning:base-conda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }}
-        timeout-minutes: 85
+        timeout-minutes: 95
 
       # report failure to Slack
       - name: Slack notification

dockers/base-conda/Dockerfile

@@ -72,16 +72,15 @@ COPY environment.yml environment.yml
 
 # conda init
 RUN conda update -n base -c defaults conda && \
-    conda install mamba -n base -c conda-forge && \
-    mamba create -y --name $CONDA_ENV python=${PYTHON_VERSION} pytorch=${PYTORCH_VERSION} torchvision torchtext cudatoolkit=${CUDA_VERSION} -c nvidia -c pytorch -c pytorch-test -c pytorch-nightly && \
+    conda create -y --name $CONDA_ENV python=${PYTHON_VERSION} pytorch=${PYTORCH_VERSION} torchvision torchtext cudatoolkit=${CUDA_VERSION} -c nvidia -c pytorch -c pytorch-test -c pytorch-nightly && \
     conda init bash && \
     # NOTE: this requires that the channel is presented in the yaml before packages \
     printf "import re;\nfname = 'environment.yml';\nreq = open(fname).read();\nfor n in ['python', 'pytorch', 'torchtext', 'torchvision']:\n    req = re.sub(rf'- {n}[>=]+', f'# - {n}=', req);\nopen(fname, 'w').write(req)" > prune.py && \
     python prune.py && \
     rm prune.py && \
     cat environment.yml && \
-    mamba env update --name $CONDA_ENV --file environment.yml && \
-    mamba clean -ya && \
+    conda env update --name $CONDA_ENV --file environment.yml && \
+    conda clean -ya && \
     rm environment.yml
 
 ENV \