Remove V100 from test environment #3717
ci.yaml
on: pull_request
metadata
0s
Matrix: amd64 / test-distribution
Matrix: arm64 / test-distribution
amd64
/
...
/
launch-slurm-runner
0s
amd64
/
...
/
jax-A100-unit-test
0s
amd64
/
test-nsys-jax-eks
5m 16s
amd64
/
...
/
launch-slurm-runner
0s
amd64
/
...
/
nsys-jax-A100-unit-test
0s
arm64
/
test-nsys-jax-eks
0s
arm64
/
...
/
run-unit-test
arm64
/
...
/
launch-slurm-runner
arm64
/
...
/
run-unit-test
arm64
/
...
/
launch-slurm-runner
amd64
/
...
/
run-unit-test
amd64
/
...
/
launch-slurm-runner
Matrix: amd64 / test-upstream-pax / pax-multi-node
Waiting for pending jobs
Matrix: amd64 / test-upstream-pax / single-process-evaluation
Waiting for pending jobs
Matrix: amd64 / test-upstream-pax / single-process-multi-device
Waiting for pending jobs
Matrix: amd64 / test-te-multigpu / te-multi-gpu
Waiting for pending jobs
Matrix: amd64 / test-upstream-t5x / t5x-multi-gpu
Matrix: amd64 / test-upstream-t5x / t5x-multi-node
Matrix: amd64 / test-maxtext / maxtext-multinode
Matrix: amd64 / test-maxtext / single-process-multi-device
amd64
/
...
/
launch-slurm-runner
0s
amd64
/
...
/
gemma-A100-unit-test
0s
amd64
/
...
/
launch-slurm-runner
0s
amd64
/
...
/
levanter-A100-unit-test
0s
amd64
/
...
/
launch-slurm-runner
0s
amd64
/
...
/
triton-A100-unit-test
0s
Matrix: amd64 / test-nsys-jax-archive
arm64
/
...
/
run-unit-test
arm64
/
...
/
launch-slurm-runner
Matrix: arm64 / test-upstream-pax / pax-multi-node
Waiting for pending jobs
Matrix: arm64 / test-upstream-pax / single-process-evaluation
Waiting for pending jobs
Matrix: arm64 / test-upstream-pax / single-process-multi-device
Waiting for pending jobs
Matrix: arm64 / test-te-multigpu / te-multi-gpu
Waiting for pending jobs
Matrix: arm64 / test-upstream-t5x / t5x-multi-gpu
Waiting for pending jobs
Matrix: arm64 / test-upstream-t5x / t5x-multi-node
Waiting for pending jobs
Matrix: arm64 / test-maxtext / maxtext-multinode
Waiting for pending jobs
Matrix: arm64 / test-maxtext / single-process-multi-device
Waiting for pending jobs
arm64
/
...
/
run-unit-test
arm64
/
...
/
launch-slurm-runner
arm64
/
...
/
run-unit-test
arm64
/
...
/
launch-slurm-runner
arm64
/
...
/
run-unit-test
arm64
/
...
/
launch-slurm-runner
Matrix: arm64 / test-nsys-jax-archive
Matrix: amd64 / test-rosetta-pax / rosetta-pax-multi-node-te
Waiting for pending jobs
Matrix: amd64 / test-rosetta-pax / rosetta-pax-multi-node
Waiting for pending jobs
Matrix: amd64 / test-rosetta-pax / rosetta-pax-single-node-dropout-te
Waiting for pending jobs
Matrix: amd64 / test-rosetta-pax / single-process-evaluation-te
Waiting for pending jobs
Matrix: amd64 / test-rosetta-pax / single-process-multi-device-te
Waiting for pending jobs
Matrix: amd64 / test-rosetta-t5x / multi-gpu-multi-node
Waiting for pending jobs
Matrix: amd64 / test-rosetta-t5x / single-process-multi-device
Waiting for pending jobs
Matrix: amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node
Waiting for pending jobs
Matrix: amd64 / test-rosetta-t5x / vit-single-process-multi-device
Waiting for pending jobs
Matrix: arm64 / test-rosetta-pax / rosetta-pax-multi-node-te
Waiting for pending jobs
Matrix: arm64 / test-rosetta-pax / rosetta-pax-multi-node
Waiting for pending jobs
Matrix: arm64 / test-rosetta-pax / rosetta-pax-single-node-dropout-te
Waiting for pending jobs
Matrix: arm64 / test-rosetta-pax / single-process-evaluation-te
Waiting for pending jobs
Matrix: arm64 / test-rosetta-pax / single-process-multi-device-te
Waiting for pending jobs
Matrix: arm64 / test-rosetta-t5x / multi-gpu-multi-node
Waiting for pending jobs
Matrix: arm64 / test-rosetta-t5x / single-process-multi-device
Waiting for pending jobs
Matrix: arm64 / test-rosetta-t5x / vit-multi-gpu-multi-node
Waiting for pending jobs
Matrix: arm64 / test-rosetta-t5x / vit-single-process-multi-device
Waiting for pending jobs
Matrix: publish-containers
Waiting for pending jobs
finalize
/
publish-badge
Annotations
20 errors
amd64 / build-upstream-pax / build-upstream-pax
buildx failed with: ERROR: failed to solve: process "/bin/sh -c <<\"EOF\" bash -exu -o pipefail\ngit-clone.sh ${URLREF_LINGVO} ${SRC_PATH_LINGVO}\npushd ${SRC_PATH_LINGVO}\n\nCPU_ARCH=\"$(dpkg --print-architecture)\"\nif [[ \"${CPU_ARCH}\" == \"arm64\" ]]; then\n\n# Use aarch distribution of protobufs\npatch -p1 <<\"EOFINNER\"\ndiff --git a/lingvo/repo.bzl b/lingvo/repo.bzl\nindex ce65822d2..d9c0277aa 100644\n--- a/lingvo/repo.bzl\n+++ b/lingvo/repo.bzl\n@@ -232,9 +232,9 @@ filegroup(\n )\n \"\"\",\n urls = [\n- \"https://github.com/protocolbuffers/protobuf/releases/download/v21.9/protoc-21.9-linux-x86_64.zip\",\n+ \"https://github.com/protocolbuffers/protobuf/releases/download/v21.9/protoc-21.9-linux-aarch_64.zip\",\n ],\n- sha256 = \"3cd951aff8ce713b94cde55e12378f505f2b89d47bf080508cf77e3934f680b6\",\n+ sha256 = \"a584286dfa8ebb17032ece206ed74d5e9931e2edb9016e427be2a0dab3b21071\",\n )\n\n def icu():\nEOFINNER\n\nfi\n\npip install tensorflow_datasets==4.9.2 auditwheel tensorflow==2.18.0\nfor pattern in \\\n \"s|tensorflow=|#tensorflow=|g\" \\\n \"s|dataclasses=|#dataclasses=|g\" \\\n \"s|==.*||g\" \\\n; do\n sed -i \"${pattern}\" ${SRC_PATH_LINGVO}/docker/dev.requirements.txt\ndone\n# Lingvo support only python < 3.12, so we hack it and update dependencies\n# to be able to build for py-3.12\nfor pattern in \\\n \"s|tensorflow-text~=2.13.0|tensorflow-text~=2.18.1|g\" \\\n \"s|tensorflow~=2.13.0|tensorflow~=2.18.0|g\" \\\n \"s|python_requires='>=3.8,<3.11'|python_requires='>=3.8,<3.13'|\" \\\n; do\n sed -i \"${pattern}\" ${SRC_PATH_LINGVO}/pip_package/setup.py;\ndone\npip install -r docker/dev.requirements.txt\n\n# Some tests are flaky right now, so we skip running the tests.\nBUILD_ARCH=\"x86_64\"\nif [[ \"$CPU_ARCH\" == \"arm64\" ]]; then\n BUILD_ARCH=\"aarch64\";\nfi\nsed -i 's/manylinux2014_x86_64/manylinux_2_38_'\"${BUILD_ARCH}\"'/' pip_package/build.sh\nSKIP_TESTS=1 PYTHON_MINOR_VERSION=$(python --version | cut -d ' ' -f 2 | cut -d '.' -f 2) pip_package/build.sh\nEOF" did not complete successfully: exit code: 1
|
arm64 / build-upstream-pax / build-upstream-pax
buildx failed with: ERROR: failed to solve: process "/bin/sh -c <<\"EOF\" bash -exu -o pipefail\ngit-clone.sh ${URLREF_LINGVO} ${SRC_PATH_LINGVO}\npushd ${SRC_PATH_LINGVO}\n\nCPU_ARCH=\"$(dpkg --print-architecture)\"\nif [[ \"${CPU_ARCH}\" == \"arm64\" ]]; then\n\n# Use aarch distribution of protobufs\npatch -p1 <<\"EOFINNER\"\ndiff --git a/lingvo/repo.bzl b/lingvo/repo.bzl\nindex ce65822d2..d9c0277aa 100644\n--- a/lingvo/repo.bzl\n+++ b/lingvo/repo.bzl\n@@ -232,9 +232,9 @@ filegroup(\n )\n \"\"\",\n urls = [\n- \"https://github.com/protocolbuffers/protobuf/releases/download/v21.9/protoc-21.9-linux-x86_64.zip\",\n+ \"https://github.com/protocolbuffers/protobuf/releases/download/v21.9/protoc-21.9-linux-aarch_64.zip\",\n ],\n- sha256 = \"3cd951aff8ce713b94cde55e12378f505f2b89d47bf080508cf77e3934f680b6\",\n+ sha256 = \"a584286dfa8ebb17032ece206ed74d5e9931e2edb9016e427be2a0dab3b21071\",\n )\n\n def icu():\nEOFINNER\n\nfi\n\npip install tensorflow_datasets==4.9.2 auditwheel tensorflow==2.18.0\nfor pattern in \\\n \"s|tensorflow=|#tensorflow=|g\" \\\n \"s|dataclasses=|#dataclasses=|g\" \\\n \"s|==.*||g\" \\\n; do\n sed -i \"${pattern}\" ${SRC_PATH_LINGVO}/docker/dev.requirements.txt\ndone\n# Lingvo support only python < 3.12, so we hack it and update dependencies\n# to be able to build for py-3.12\nfor pattern in \\\n \"s|tensorflow-text~=2.13.0|tensorflow-text~=2.18.1|g\" \\\n \"s|tensorflow~=2.13.0|tensorflow~=2.18.0|g\" \\\n \"s|python_requires='>=3.8,<3.11'|python_requires='>=3.8,<3.13'|\" \\\n; do\n sed -i \"${pattern}\" ${SRC_PATH_LINGVO}/pip_package/setup.py;\ndone\npip install -r docker/dev.requirements.txt\n\n# Some tests are flaky right now, so we skip running the tests.\nBUILD_ARCH=\"x86_64\"\nif [[ \"$CPU_ARCH\" == \"arm64\" ]]; then\n BUILD_ARCH=\"aarch64\";\nfi\nsed -i 's/manylinux2014_x86_64/manylinux_2_38_'\"${BUILD_ARCH}\"'/' pip_package/build.sh\nSKIP_TESTS=1 PYTHON_MINOR_VERSION=$(python --version | cut -d ' ' -f 2 | cut -d '.' -f 2) pip_package/build.sh\nEOF" did not complete successfully: exit code: 1
|
amd64 / test-jax / jax-A100-unit-test
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / test-nsys-jax / nsys-jax-A100-unit-test
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / test-gemma / gemma-A100-unit-test
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / test-levanter / levanter-A100-unit-test
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / test-upstream-t5x / t5x-multi-gpu (1P8G, 8)
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / test-upstream-t5x / t5x-multi-node (8G2N, 8, 2)
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / test-nsys-jax / runner / launch-slurm-runner
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / test-jax / runner / launch-slurm-runner
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / test-maxtext / single-process-multi-device (1, 1, 2, 4)
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / test-maxtext / maxtext-multinode (1, 1, 1, 1)
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / test-triton / triton-A100-unit-test
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / test-gemma / runner / launch-slurm-runner
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / test-levanter / runner / launch-slurm-runner
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / test-triton / runner / launch-slurm-runner
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / build-rosetta-t5x / build-rosetta
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
amd64 / build-rosetta-t5x / build-rosetta
The operation was canceled.
|
arm64 / build-upstream-t5x / build-upstream-t5x
Canceling since a higher priority waiting request for 'CI-vkozlov/remove-v100' exists
|
arm64 / build-upstream-t5x / build-upstream-t5x
The operation was canceled.
|
Artifacts
Produced during runtime
Name | Size | |
---|---|---|
artifact-base-build-amd64
|
567 Bytes |
|
artifact-base-build-arm64
|
566 Bytes |
|
artifact-equinox-build-amd64
|
570 Bytes |
|
artifact-equinox-build-arm64
|
570 Bytes |
|
artifact-gemma-build-amd64
|
561 Bytes |
|
artifact-jax-build-amd64
|
553 Bytes |
|
artifact-jax-build-arm64
|
554 Bytes |
|
artifact-levanter-build-amd64
|
571 Bytes |
|
artifact-levanter-build-arm64
|
572 Bytes |
|
artifact-maxtext-build-amd64
|
568 Bytes |
|
artifact-maxtext-build-arm64
|
567 Bytes |
|
artifact-pax-build-amd64
|
472 Bytes |
|
artifact-pax-build-arm64
|
471 Bytes |
|
artifact-t5x-build-amd64
|
568 Bytes |
|
artifact-triton-build-amd64
|
564 Bytes |
|
bumped-manifest
|
82.1 KB |
|