CI #3525
ci.yaml
on: schedule
metadata
0s
Matrix: amd64 / test-distribution
Matrix: arm64 / test-distribution
Matrix: amd64 / test-jax / run-unit-test
Matrix: amd64 / test-nsys-jax / run-unit-test
Matrix: amd64 / test-pallas / run-unit-test
amd64
/
...
/
launch-slurm-runner
31m 10s
amd64
/
...
/
launch-slurm-runner
51m 9s
amd64
/
...
/
launch-slurm-runner
25m 24s
Matrix: arm64 / test-jax / run-unit-test
Waiting for pending jobs
Matrix: arm64 / test-nsys-jax / run-unit-test
Waiting for pending jobs
Matrix: arm64 / test-pallas / run-unit-test
Waiting for pending jobs
arm64
/
...
/
launch-slurm-runner
arm64
/
...
/
launch-slurm-runner
arm64
/
...
/
launch-slurm-runner
Matrix: amd64 / test-te / run-unit-test
Matrix: amd64 / test-upstream-pax / pax-multi-node
Matrix: amd64 / test-upstream-pax / single-process-evaluation
Matrix: amd64 / test-upstream-pax / single-process-multi-device
Matrix: amd64 / test-te-multigpu / te-multi-gpu
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
Waiting for pending jobs
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: amd64 / test-rosetta-pax / rosetta-pax-multi-node-te
Matrix: amd64 / test-rosetta-pax / rosetta-pax-multi-node
Matrix: amd64 / test-rosetta-pax / rosetta-pax-single-node-dropout-te
Matrix: amd64 / test-rosetta-pax / single-process-evaluation-te
Matrix: amd64 / test-rosetta-pax / single-process-multi-device-te
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
3s
Annotations
32 errors and 2 warnings
amd64 / build-triton / build-triton
buildx failed with: ERROR: failed to solve: process "/bin/sh -c <<\"EOF\" bash -ex\npushd /opt/checkout/external/triton\nmkdir dist\n# Make sure the wheel is labelled as 3.1 (it is ~HEAD), not 3.0. The upstream branch\n# structure seems to have a 3.1 release branch that has not been merged back to main.\nsed -i -e 's|version=\"3\\.0\\.0\"|version=\"3.1.0\"|g' python/setup.py\n# Do not compile with -Werror\nsed -i -e 's|-Werror||g' CMakeLists.txt\n# The LLVM build above does not enable these libraries\nsed -i -e 's|\\(LLVMAMDGPU.*\\)|# \\1|g' CMakeLists.txt\n# Do not build tests\nsed -i -e 's|^\\s*add_subdirectory(unittest)|# unit tests disabled|' CMakeLists.txt\n# Avoid error due to forward declaration of Module\nsed -i -e '/#include \"llvm\\/IR\\/IRBuilder.h\"/a #include \"llvm/IR/Module.h\"' test/lib/Instrumentation/GPUHello.cpp\n# Google has patches that mess with include paths in source files\nsed -i -e '/include_directories(${PROJECT_SOURCE_DIR}\\/third_party)/a include_directories(${PROJECT_SOURCE_DIR}/third_party/amd/include)' CMakeLists.txt\nsed -i -e '/include_directories(${PROJECT_BINARY_DIR}\\/third_party)/a include_directories(${PROJECT_BINARY_DIR}/third_party/amd/include)' CMakeLists.txt\nsed -i -e '/include_directories(${PROJECT_SOURCE_DIR}\\/third_party)/a include_directories(${PROJECT_SOURCE_DIR}/third_party/nvidia/include)' CMakeLists.txt\nsed -i -e '/include_directories(${PROJECT_BINARY_DIR}\\/third_party)/a include_directories(${PROJECT_BINARY_DIR}/third_party/nvidia/include)' CMakeLists.txt\n# Extra patches to Triton maintained in XLA. These are already applied in the working directory.\nXLA_TRITON_PATCHES=\"${SRC_PATH_XLA}/third_party/triton\"\n# Use clang to match Google etc.\nLLVM_INCLUDE_DIRS=/opt/llvm-build/include \\\n LLVM_LIBRARY_DIR=/opt/llvm-build/lib \\\n LLVM_SYSPATH=/opt/llvm-build \\\n TRITON_BUILD_WITH_CLANG_LLD=1 \\\n pip wheel --verbose --wheel-dir=dist/ python/\n# Clean up the wheel build directory so it doesn't end up bloating the container\nrm -rf python/build\nEOF" did not complete successfully: exit code: 1
|
amd64 / test-levanter / levanter-V100-unit-test
Process completed with exit code 1.
|
amd64 / test-levanter / levanter-A100-unit-test
Process completed with exit code 1.
|
amd64 / test-gemma / gemma-V100-unit-test
Process completed with exit code 1.
|
amd64 / test-gemma / gemma-A100-unit-test
Process completed with exit code 1.
|
amd64 / test-upstream-t5x / t5x-multi-node (8G2N, 8, 2)
The job running on runner jumpbox-vc69x-bp2pj 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-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-pks9d has exceeded the maximum execution time of 360 minutes.
|
|
amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node (1, 2)
The job running on runner jumpbox-vc69x-8r7fq 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-pax / rosetta-pax-multi-node (4, 2, 1, 2)
The job running on runner jumpbox-vc69x-g5cw8 has exceeded the maximum execution time of 360 minutes.
|
amd64 / test-rosetta-pax / rosetta-pax-multi-node (4, 2, 1, 2)
The operation was canceled.
|
amd64 / test-rosetta-pax / rosetta-pax-multi-node-te (16DP1FSDP1TP1PP_TE, 1, 16, 1, 1, 4)
The job running on runner jumpbox-vc69x-47j9x has exceeded the maximum execution time of 360 minutes.
|
amd64 / test-rosetta-pax / rosetta-pax-multi-node-te (16DP1FSDP1TP1PP_TE, 1, 16, 1, 1, 4)
The operation was canceled.
|
amd64 / test-maxtext / maxtext-multinode (1, 4, 2, 2)
The job running on runner jumpbox-vc69x-m48c7 has exceeded the maximum execution time of 360 minutes.
|
amd64 / test-maxtext / maxtext-multinode (1, 4, 2, 2)
The operation was canceled.
|
amd64 / test-maxtext / test-maxtext-outcome
Process completed with exit code 1.
|
amd64 / test-upstream-pax / pax-multi-node (16DP1FSDP1TP1PP, 1, 16, 1, 1, 4)
The job running on runner jumpbox-vc69x-bbtd7 has exceeded the maximum execution time of 360 minutes.
|
amd64 / test-upstream-pax / pax-multi-node (16DP1FSDP1TP1PP, 1, 16, 1, 1, 4)
The operation was canceled.
|
amd64 / test-rosetta-pax / test-pax-rosetta-outcome
Process completed with exit code 1.
|
amd64 / test-upstream-t5x / t5x-multi-node (8G2N_fmha, 8, 2, --enable-fmha 1)
The job running on runner jumpbox-vc69x-s6xgk 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 / multi-gpu-multi-node (2N2G_te-0, 2, 2, --enable-te 0)
The job running on runner jumpbox-vc69x-fzqbk 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 / vit-multi-gpu-multi-node (8, 2)
The job running on runner jumpbox-vc69x-ghhsm 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 / test-t5x-rosetta-outcome
Process completed with exit code 1.
|
amd64 / test-upstream-pax / pax-multi-node (2DP1FSDP2TP4PP, 4, 2, 1, 2, 4)
The job running on runner jumpbox-vc69x-lfw44 has exceeded the maximum execution time of 360 minutes.
|
amd64 / test-upstream-pax / pax-multi-node (2DP1FSDP2TP4PP, 4, 2, 1, 2, 4)
The operation was canceled.
|
amd64 / test-upstream-pax / test-upstream-pax-outcome
Process completed with exit code 1.
|
merge-new-manifest
Unexpected input(s) 'owner_and_repo', valid inputs are ['route', 'mediaType']
|
merge-new-manifest
Unexpected input(s) 'owner_and_repo', 'head', 'base', 'body', 'title', 'draft', valid inputs are ['route', 'mediaType']
|
Artifacts
Produced during runtime
Name | Size | |
---|---|---|
artifact-base-build-amd64
|
566 Bytes |
|
artifact-base-build-arm64
|
566 Bytes |
|
artifact-equinox-build-amd64
|
570 Bytes |
|
artifact-equinox-build-arm64
|
569 Bytes |
|
artifact-final-report
|
5.29 KB |
|
artifact-gemma-build-amd64
|
560 Bytes |
|
artifact-jax-build-amd64
|
553 Bytes |
|
artifact-jax-build-arm64
|
553 Bytes |
|
artifact-levanter-build-amd64
|
572 Bytes |
|
artifact-levanter-build-arm64
|
572 Bytes |
|
artifact-maxtext-build-amd64
|
567 Bytes |
|
artifact-maxtext-build-arm64
|
569 Bytes |
|
artifact-maxtext-test
|
654 Bytes |
|
artifact-pax-build-amd64
|
567 Bytes |
|
artifact-pax-build-arm64
|
567 Bytes |
|
artifact-rosetta-build-pax-amd64
|
583 Bytes |
|
artifact-rosetta-build-pax-arm64
|
584 Bytes |
|
artifact-rosetta-build-t5x-amd64
|
586 Bytes |
|
artifact-rosetta-build-t5x-arm64
|
585 Bytes |
|
artifact-rosetta-pax-mgmn-test
|
723 Bytes |
|
artifact-rosetta-t5x-mgmn-test
|
658 Bytes |
|
artifact-t5x-build-amd64
|
570 Bytes |
|
artifact-t5x-build-arm64
|
567 Bytes |
|
artifact-triton-build-amd64
|
469 Bytes |
|
artifact-upstream-pax-mgmn-test
|
688 Bytes |
|
artifact-upstream-t5x-mgmn-test
|
634 Bytes |
|
artifact-workflow-metadata
|
277 Bytes |
|
bumped-manifest
|
71.8 KB |
|
final-base
|
249 Bytes |
|
final-equinox
|
258 Bytes |
|
final-gemma
|
252 Bytes |
|
final-jax
|
246 Bytes |
|
final-levanter
|
261 Bytes |
|
final-maxtext
|
258 Bytes |
|
final-pax
|
246 Bytes |
|
final-t5x
|
246 Bytes |
|
final-upstream-pax
|
273 Bytes |
|
final-upstream-t5x
|
273 Bytes |
|
gemma-unit-test-A100
|
1.94 KB |
|
gemma-unit-test-V100
|
1.94 KB |
|
jax-unit-test-A100
|
19 KB |
|
jax-unit-test-V100
|
24.8 KB |
|
levanter-unit-test-A100
|
13 KB |
|
levanter-unit-test-V100
|
15.3 KB |
|
mealkit-equinox
|
270 Bytes |
|
mealkit-gemma
|
263 Bytes |
|
mealkit-jax
|
256 Bytes |
|
mealkit-levanter
|
272 Bytes |
|
mealkit-maxtext
|
268 Bytes |
|
mealkit-pax
|
258 Bytes |
|
mealkit-t5x
|
258 Bytes |
|
mealkit-upstream-pax
|
282 Bytes |
|
mealkit-upstream-t5x
|
283 Bytes |
|
nsys-jax-unit-test-A100
|
29.4 MB |
|
nsys-jax-unit-test-V100
|
16.1 MB |
|
pallas-unit-test-A100
|
7.65 KB |
|
pallas-unit-test-V100
|
7.5 KB |
|
rosetta-pax-11834427231-1DP1FSDP1TP1PP_TE
|
92.3 KB |
|
rosetta-pax-11834427231-1DP2FSDP4TP1PP_single_process_TE
|
112 KB |
|
rosetta-pax-11834427231-1DP8FSDP1TP1PP_TE
|
374 KB |
|
rosetta-pax-11834427231-2DP1FSDP1TP4PP
|
297 KB |
|
rosetta-pax-11834427231-4DP1FSDP2TP1PP
|
400 KB |
|
rosetta-pax-11834427231-4DP1FSDP2TP1PP_TE
|
374 KB |
|
rosetta-pax-11834427231-5B_fused_attn_0
|
423 KB |
|
rosetta-pax-11834427231-5B_fused_attn_1
|
434 KB |
|
rosetta-pax-11834427231-8DP1FSDP1TP1PP
|
397 KB |
|
rosetta-pax-11834427231-8DP1FSDP1TP1PP_TE
|
373 KB |
|
rosetta-pax-11834427231-8DP1FSDP1TP1PP_eval_TE
|
83.6 KB |
|
rosetta-pax-11834427231-8DP1FSDP1TP1PP_single_process_TE
|
112 KB |
|
rosetta-pax-11834427231-8DP_TE_dropout
|
373 KB |
|
rosetta-pax-11834427231-LLaMA_eval_TE
|
248 KB |
|
rosetta-t5x-11834427231-1P1G_te-0
|
35 KB |
|
rosetta-t5x-11834427231-1P8G_te-1
|
35.1 KB |
|
rosetta-t5x-vit-11834427231-VIT1G1N
|
21.5 KB |
|
rosetta-t5x-vit-11834427231-VIT1P8G
|
21.8 KB |
|
rosetta-t5x-vit-11834427231-VIT8G1N
|
32.3 KB |
|
te-2GPU
|
5.34 KB |
|
te-4GPU
|
5.38 KB |
|
te-8GPU
|
5.44 KB |
|
te-multigpu-test
|
528 Bytes |
|
te-unit-test-A100
|
839 KB |
|
te-unit-test-V100
|
679 KB |
|
upstream-maxtext-11834427231-1DP1FSDP1TP1PP
|
14.5 KB |
|
upstream-maxtext-11834427231-1DP1FSDP8TP1PP
|
20.6 KB |
|
upstream-maxtext-11834427231-1DP2FSDP4TP1PP_single_process
|
14.9 KB |
|
upstream-maxtext-11834427231-1DP4FSDP2TP1PP
|
20.7 KB |
|
upstream-maxtext-11834427231-1DP8FSDP1TP1PP
|
20.6 KB |
|
upstream-maxtext-11834427231-2DP2FSDP2TP1PP
|
20.8 KB |
|
upstream-pax-11834427231-1DP1FSDP1TP1PP
|
147 KB |
|
upstream-pax-11834427231-1DP2FSDP4TP1PP_single_process
|
147 KB |
|
upstream-pax-11834427231-1DP8FSDP1TP1PP
|
455 KB |
|
upstream-pax-11834427231-2DP1FSDP1TP4PP
|
318 KB |
|
upstream-pax-11834427231-4DP1FSDP2TP1PP
|
454 KB |
|
upstream-pax-11834427231-8DP1FSDP1TP1PP
|
460 KB |
|
upstream-pax-11834427231-8DP1FSDP1TP1PP_eval
|
114 KB |
|
upstream-pax-11834427231-8DP1FSDP1TP1PP_single_process
|
147 KB |
|
upstream-pax-11834427231-LLaMA_eval
|
271 KB |
|
upstream-t5x-11834427231-1P2G_fmha
|
33.9 KB |
|
upstream-t5x-11834427231-1P8G
|
33.5 KB |
|