From 6c33b8c1a9408651cf6a5f0ba978af342f8f207d Mon Sep 17 00:00:00 2001 From: yikaiMeta <116014337+yikaiMeta@users.noreply.github.com> Date: Mon, 26 Aug 2024 10:52:03 -0400 Subject: [PATCH 01/11] Update dev-requirements.txt, Add docker-compose This fixed the slurm integration test. --- dev-requirements.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/dev-requirements.txt b/dev-requirements.txt index 144f102e9..057e16c2d 100644 --- a/dev-requirements.txt +++ b/dev-requirements.txt @@ -3,6 +3,7 @@ ax-platform[mysql]==0.2.3 boto3==1.34.51 captum>=0.4.0 docker +docker-compose kubernetes==25.3.0 flake8==3.9.0 fsspec==2024.3.1 From 159ab2e1637d04c6babdb37a5aba7c7b136451de Mon Sep 17 00:00:00 2001 From: yikaiMeta <116014337+yikaiMeta@users.noreply.github.com> Date: Mon, 26 Aug 2024 11:09:08 -0400 Subject: [PATCH 02/11] Update slurm-local-integration-tests.yaml --- .github/workflows/slurm-local-integration-tests.yaml | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/.github/workflows/slurm-local-integration-tests.yaml b/.github/workflows/slurm-local-integration-tests.yaml index f39a31132..b9abc9c56 100644 --- a/.github/workflows/slurm-local-integration-tests.yaml +++ b/.github/workflows/slurm-local-integration-tests.yaml @@ -23,6 +23,10 @@ jobs: architecture: x64 - name: Checkout TorchX uses: actions/checkout@v2 + - name: Install Dependencies + run: + set -ex + pip install wheel - name: Checkout slurm-docker-cluster run: | set -ex @@ -49,11 +53,6 @@ jobs: set -ex cd slurm-docker-cluster IMAGE_TAG=$SLURM_VERSION docker-compose up --detach - - name: Install Dependencies - run: - set -ex - - pip install wheel - name: Run Slurm Integration Tests run: | set -e From 774a485983a71fe57f85a12f98bf1999a48f9b38 Mon Sep 17 00:00:00 2001 From: yikaiMeta <116014337+yikaiMeta@users.noreply.github.com> Date: Mon, 26 Aug 2024 12:10:51 -0400 Subject: [PATCH 03/11] Update dev-requirements.txt --- dev-requirements.txt | 1 - 1 file changed, 1 deletion(-) diff --git a/dev-requirements.txt b/dev-requirements.txt index 057e16c2d..144f102e9 100644 --- a/dev-requirements.txt +++ b/dev-requirements.txt @@ -3,7 +3,6 @@ ax-platform[mysql]==0.2.3 boto3==1.34.51 captum>=0.4.0 docker -docker-compose kubernetes==25.3.0 flake8==3.9.0 fsspec==2024.3.1 From 9511f369204d74b4664be0c835d172aafcce8245 Mon Sep 17 00:00:00 2001 From: yikaiMeta <116014337+yikaiMeta@users.noreply.github.com> Date: Mon, 26 Aug 2024 12:13:03 -0400 Subject: [PATCH 04/11] Update slurm-local-integration-tests.yaml --- .github/workflows/slurm-local-integration-tests.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/slurm-local-integration-tests.yaml b/.github/workflows/slurm-local-integration-tests.yaml index b9abc9c56..db0db222b 100644 --- a/.github/workflows/slurm-local-integration-tests.yaml +++ b/.github/workflows/slurm-local-integration-tests.yaml @@ -38,7 +38,7 @@ jobs: set -ex cd slurm-docker-cluster - docker-compose pull --ignore-pull-failures + docker compose pull --ignore-pull-failures continue-on-error: true # cache layers to avoid rebuilding slurm - uses: satackey/action-docker-layer-caching@v0.0.11 @@ -52,7 +52,7 @@ jobs: run: | set -ex cd slurm-docker-cluster - IMAGE_TAG=$SLURM_VERSION docker-compose up --detach + IMAGE_TAG=$SLURM_VERSION docker compose up --detach - name: Run Slurm Integration Tests run: | set -e From 6fd0e24bd1dbad7cfe84180394d648bea58dcbbc Mon Sep 17 00:00:00 2001 From: yikaiMeta <116014337+yikaiMeta@users.noreply.github.com> Date: Mon, 26 Aug 2024 15:43:05 -0400 Subject: [PATCH 05/11] Update dev-requirements.txt --- dev-requirements.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/dev-requirements.txt b/dev-requirements.txt index 144f102e9..163e41e67 100644 --- a/dev-requirements.txt +++ b/dev-requirements.txt @@ -31,6 +31,7 @@ torchtext==0.17.1 torchvision==0.17.1 ts==0.5.1 ray[default] +wheel # lint (linter versions are managed by lintrunner) lintrunner From b0b14f690e9fbda511e3f707f3723b2358a94695 Mon Sep 17 00:00:00 2001 From: yikaiMeta <116014337+yikaiMeta@users.noreply.github.com> Date: Tue, 27 Aug 2024 14:34:55 -0400 Subject: [PATCH 06/11] Update slurm-local-integration-tests.yaml --- .github/workflows/slurm-local-integration-tests.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/slurm-local-integration-tests.yaml b/.github/workflows/slurm-local-integration-tests.yaml index db0db222b..d51290c3e 100644 --- a/.github/workflows/slurm-local-integration-tests.yaml +++ b/.github/workflows/slurm-local-integration-tests.yaml @@ -27,6 +27,7 @@ jobs: run: set -ex pip install wheel + pip3 install wheel - name: Checkout slurm-docker-cluster run: | set -ex From f0d7bf2019c6dcc1ed9eec34d070da13781fe162 Mon Sep 17 00:00:00 2001 From: yikaiMeta <116014337+yikaiMeta@users.noreply.github.com> Date: Tue, 27 Aug 2024 14:36:33 -0400 Subject: [PATCH 07/11] Update slurmdockerint.sh --- scripts/slurmdockerint.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/scripts/slurmdockerint.sh b/scripts/slurmdockerint.sh index 80bd8f58c..97302bece 100755 --- a/scripts/slurmdockerint.sh +++ b/scripts/slurmdockerint.sh @@ -11,6 +11,7 @@ DIST=dist rm -r $DIST || true python setup.py bdist_wheel +python3 setup.py bdist_wheel WHEEL="$DIST/$(ls $DIST)" From cfdd677d2a75353b7784ee92847301692743f0c4 Mon Sep 17 00:00:00 2001 From: yikaiMeta <116014337+yikaiMeta@users.noreply.github.com> Date: Mon, 2 Sep 2024 00:02:58 -0400 Subject: [PATCH 08/11] Update slurmdockerint.sh --- scripts/slurmdockerint.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/slurmdockerint.sh b/scripts/slurmdockerint.sh index 97302bece..8cc53da8d 100755 --- a/scripts/slurmdockerint.sh +++ b/scripts/slurmdockerint.sh @@ -10,8 +10,8 @@ set -ex DIST=dist rm -r $DIST || true -python setup.py bdist_wheel -python3 setup.py bdist_wheel +# python setup.py bdist_wheel +# python3 setup.py bdist_wheel WHEEL="$DIST/$(ls $DIST)" From 8b7c78bbb8f5e7f94341be6b7d421b200491d1f7 Mon Sep 17 00:00:00 2001 From: yikaiMeta <116014337+yikaiMeta@users.noreply.github.com> Date: Mon, 9 Sep 2024 16:27:09 -0400 Subject: [PATCH 09/11] Update slurm-local-integration-tests.yaml --- .github/workflows/slurm-local-integration-tests.yaml | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/.github/workflows/slurm-local-integration-tests.yaml b/.github/workflows/slurm-local-integration-tests.yaml index d51290c3e..0c074d7c7 100644 --- a/.github/workflows/slurm-local-integration-tests.yaml +++ b/.github/workflows/slurm-local-integration-tests.yaml @@ -23,11 +23,6 @@ jobs: architecture: x64 - name: Checkout TorchX uses: actions/checkout@v2 - - name: Install Dependencies - run: - set -ex - pip install wheel - pip3 install wheel - name: Checkout slurm-docker-cluster run: | set -ex @@ -54,6 +49,10 @@ jobs: set -ex cd slurm-docker-cluster IMAGE_TAG=$SLURM_VERSION docker compose up --detach + - name: Install Dependencies + run: + set -ex + pip install wheel - name: Run Slurm Integration Tests run: | set -e From fe1cfe6b5fc0f502312af1ca7bc57ab8b1434f77 Mon Sep 17 00:00:00 2001 From: yikaiMeta <116014337+yikaiMeta@users.noreply.github.com> Date: Mon, 9 Sep 2024 16:28:41 -0400 Subject: [PATCH 10/11] Update slurmdockerint.sh --- scripts/slurmdockerint.sh | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/scripts/slurmdockerint.sh b/scripts/slurmdockerint.sh index 8cc53da8d..80bd8f58c 100755 --- a/scripts/slurmdockerint.sh +++ b/scripts/slurmdockerint.sh @@ -10,8 +10,7 @@ set -ex DIST=dist rm -r $DIST || true -# python setup.py bdist_wheel -# python3 setup.py bdist_wheel +python setup.py bdist_wheel WHEEL="$DIST/$(ls $DIST)" From b45350b9d9d0c2c7af674e2754709f304dfb992f Mon Sep 17 00:00:00 2001 From: yikaiMeta <116014337+yikaiMeta@users.noreply.github.com> Date: Mon, 9 Sep 2024 21:51:44 -0400 Subject: [PATCH 11/11] Update slurm-local-integration-tests.yaml --- .github/workflows/slurm-local-integration-tests.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/slurm-local-integration-tests.yaml b/.github/workflows/slurm-local-integration-tests.yaml index 0c074d7c7..e8ef0d821 100644 --- a/.github/workflows/slurm-local-integration-tests.yaml +++ b/.github/workflows/slurm-local-integration-tests.yaml @@ -50,7 +50,7 @@ jobs: cd slurm-docker-cluster IMAGE_TAG=$SLURM_VERSION docker compose up --detach - name: Install Dependencies - run: + run: | set -ex pip install wheel - name: Run Slurm Integration Tests