Replace deprecated flag xla_gpu_graph_level. #3720
ci.yaml
on: pull_request
metadata
0s
Matrix: amd64 / test-distribution
Matrix: arm64 / test-distribution
Matrix: amd64 / test-jax / run-unit-test
amd64
/
...
/
launch-slurm-runner
19m 53s
amd64
/
test-nsys-jax-eks
5m 12s
Matrix: amd64 / test-nsys-jax / run-unit-test
Matrix: arm64 / test-jax / run-unit-test
Waiting for pending jobs
arm64
/
test-nsys-jax-eks
0s
arm64
/
...
/
launch-slurm-runner
Matrix: arm64 / test-nsys-jax / run-unit-test
Waiting for pending jobs
Matrix: amd64 / test-te / run-unit-test
Waiting for pending jobs
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-gemma / run-unit-test
Matrix: amd64 / test-levanter / run-unit-test
Matrix: amd64 / test-maxtext / maxtext-multinode
Matrix: amd64 / test-maxtext / single-process-multi-device
Matrix: amd64 / test-triton / run-unit-test
Matrix: amd64 / test-nsys-jax-archive
Matrix: arm64 / test-te / run-unit-test
Waiting for pending jobs
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-gemma / run-unit-test
Waiting for pending jobs
Matrix: arm64 / test-levanter / run-unit-test
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
Matrix: arm64 / test-triton / run-unit-test
Waiting for pending jobs
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
Matrix: amd64 / test-rosetta-t5x / single-process-multi-device
Matrix: amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node
Matrix: amd64 / test-rosetta-t5x / vit-single-process-multi-device
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
finalize
/
publish-badge
2s
Annotations
22 errors
|
amd64 / test-triton / triton-V100-unit-test
Process completed with exit code 1.
|
|
amd64 / test-triton / triton-A100-unit-test
Process completed with exit code 1.
|
|
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-maxtext / maxtext-multinode (1, 4, 2, 2)
The job running on runner jumpbox-vc69x-xnvkc has exceeded the maximum execution time of 360 minutes.
|
|
amd64 / test-maxtext / maxtext-multinode (1, 4, 2, 2)
The operation was canceled.
|
|
amd64 / test-upstream-t5x / t5x-multi-node (8G2N, 8, 2)
The job running on runner jumpbox-vc69x-jlqw4 has exceeded the maximum execution time of 360 minutes.
|
|
amd64 / test-upstream-t5x / t5x-multi-node (8G2N, 8, 2)
The operation was canceled.
|
|
amd64 / test-maxtext / test-maxtext-outcome
Process completed with exit code 1.
|
|
amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node (1, 2)
The job running on runner jumpbox-vc69x-mb9vp has exceeded the maximum execution time of 360 minutes.
|
|
amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node (1, 2)
The operation was canceled.
|
|
amd64 / test-rosetta-t5x / multi-gpu-multi-node (2N8G-te-1, 8, 2, --gin.train/utils.DatasetConfig.pack=False --gin.train_eva...
The job running on runner jumpbox-vc69x-7r785 has exceeded the maximum execution time of 360 minutes.
|
|
|
|
amd64 / test-upstream-t5x / t5x-multi-node (8G2N_fmha, 8, 2, --enable-fmha 1)
The job running on runner jumpbox-vc69x-cwzfq has exceeded the maximum execution time of 360 minutes.
|
|
amd64 / test-upstream-t5x / t5x-multi-node (8G2N_fmha, 8, 2, --enable-fmha 1)
The operation was canceled.
|
|
amd64 / test-upstream-t5x / test-upstream-t5x-outcome
Process completed with exit code 1.
|
|
amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node (8, 2)
The job running on runner jumpbox-vc69x-dcqpl has exceeded the maximum execution time of 360 minutes.
|
|
amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node (8, 2)
The operation was canceled.
|
|
amd64 / test-rosetta-t5x / multi-gpu-multi-node (2N2G_te-0, 2, 2, --enable-te 0)
The job running on runner jumpbox-vc69x-xgnlm has exceeded the maximum execution time of 360 minutes.
|
|
amd64 / test-rosetta-t5x / multi-gpu-multi-node (2N2G_te-0, 2, 2, --enable-te 0)
The operation was canceled.
|
|
amd64 / test-rosetta-t5x / test-t5x-rosetta-outcome
Process completed with exit code 1.
|
|
finalize / report
Process completed with exit code 5.
|
Artifacts
Produced during runtime
| Name | Size | Digest | |
|---|---|---|---|
|
artifact-maxtext-test
Expired
|
654 Bytes |
sha256:3d0d8d6a9d3ae1acd1c54edeece0c7bcee809d9eea74e6378afac53ad601ece0
|
|
|
artifact-pax-build-amd64
Expired
|
472 Bytes |
sha256:48b2e7ead710a4278647d48865ab43f1754449297c4e1090fa61525a6352fa4d
|
|
|
artifact-pax-build-arm64
Expired
|
471 Bytes |
sha256:73f82acacc140106cd45ee39cf118e3a7acb7a7acd48091805f054b9ef639a23
|
|
|
artifact-rosetta-t5x-mgmn-test
Expired
|
645 Bytes |
sha256:9c0572b99ac16d6320beb74c67b0e6728fe24ff6fa9b02d6ae29b8808d5c9b55
|
|
|
artifact-upstream-t5x-mgmn-test
Expired
|
632 Bytes |
sha256:b9b728d771e13b48e6e851a47de1af64f794420f91ad2b26b68b85c414953755
|
|
|
artifact-workflow-metadata
Expired
|
277 Bytes |
sha256:2ae6b25deb8fd63a6a3d2780800e88abd8f4db2e50b6ebf82e80fa98d9079a54
|
|
|
final-base
Expired
|
193 Bytes |
sha256:f63c67e7b570bccb36d13ac3ce315975089f40673893c9f15068849f0b6c2d15
|
|
|
final-equinox
Expired
|
202 Bytes |
sha256:d0f6ac67ef4f20bf2eed0a98ab84e2d6bda4dbec7c1dbbb0b028f848ccf3f233
|
|
|
final-gemma
Expired
|
196 Bytes |
sha256:46520d4c0a42e30b09e2f7acc7eda5e3b5ab31f78c552c95fffe65818ff3513b
|
|
|
final-jax
Expired
|
190 Bytes |
sha256:4ee0e83ca4dcc39ac8762868cc4cbdad32b46249bd130019e51153ce26ec514f
|
|
|
final-levanter
Expired
|
205 Bytes |
sha256:fc700eb28b484a670e4926049a71dc2d586463de7f9ab76bf8444188427087f9
|
|
|
final-maxtext
Expired
|
202 Bytes |
sha256:dcab260b32e64968934e4c37944f3893f2defc6e89d80b57f1439c48cc1932a8
|
|
|
final-t5x
Expired
|
190 Bytes |
sha256:9f02ad63e0ea0766d37839fa8ed7fdc386b44ff0fe7c0fa1bcc9d5feb7e27a3a
|
|
|
final-triton
Expired
|
199 Bytes |
sha256:bc891c9de31bc903ccee57a018a480565983627168a1e320809c039ef69ec6e2
|
|
|
final-upstream-t5x
Expired
|
217 Bytes |
sha256:51e25831e113d85313721ac1d603a5bdae5a3753f3eae5fae5dacb9e8ae83eab
|
|
|
mealkit-equinox
Expired
|
214 Bytes |
sha256:9430b7cb2d1ee47b90d3677aac4ba2619142583d1353bcdfc21fb7d29629950d
|
|
|
mealkit-gemma
Expired
|
208 Bytes |
sha256:91b832fb0454677eb38433f7c127af55fcf17f29952add418592316b0b121849
|
|
|
mealkit-jax
Expired
|
199 Bytes |
sha256:5f8414227142c7865755fd17650c29d0afc41a88d39838f1ee8b7d73b9e26bb1
|
|
|
mealkit-levanter
Expired
|
217 Bytes |
sha256:db9a5a0b819ace64b7d6fa92f94cb8699e1a30026813c28b71b27325fc5a89af
|
|
|
mealkit-maxtext
Expired
|
214 Bytes |
sha256:b75fb9b2e679c4f6ec02d92e73f34df379599507bf3584dc6dfccbe7ce355c84
|
|
|
mealkit-t5x
Expired
|
202 Bytes |
sha256:e334da8d6374141b289877e08ecb857d42279730acd1fce5a2ba1b7c8ac9d52b
|
|
|
mealkit-triton
Expired
|
211 Bytes |
sha256:e58f20149026cbbdca6be30e7930c3eb82bd6f75b637cf0a3f5f8d98d3013322
|
|
|
mealkit-upstream-t5x
Expired
|
229 Bytes |
sha256:b74847c9998e230a9eeb03beb1f22035697cb8c9fc2ad1e82c2da87420290de9
|
|