Skip to content

CI

CI #3512

Triggered via schedule November 6, 2024 09:33
Status Failure
Total duration 4h 8m 54s
Artifacts 115

ci.yaml

on: schedule
metadata
3s
metadata
bump-manifest
24s
bump-manifest
Matrix: amd64 / test-distribution
Matrix: arm64 / test-distribution
amd64  /  ...  /  build-base
4m 30s
amd64 / build-base / build-base
arm64  /  ...  /  build-base
4m 30s
arm64 / build-base / build-base
amd64  /  ...  /  build-jax
21m 12s
amd64 / build-jax / build-jax
arm64  /  ...  /  build-jax
30m 14s
arm64 / build-jax / build-jax
amd64  /  ...  /  build-upstream-pax
6m 19s
amd64 / build-upstream-pax / build-upstream-pax
Matrix: amd64 / test-jax / run-unit-test
Matrix: amd64 / test-nsys-jax / run-unit-test
Matrix: amd64 / test-pallas / run-unit-test
amd64  /  ...  /  build-upstream-t5x
6m 57s
amd64 / build-upstream-t5x / build-upstream-t5x
amd64  /  ...  /  launch-slurm-runner
19m 22s
amd64 / test-jax / runner / launch-slurm-runner
amd64  /  ...  /  launch-slurm-runner
33m 20s
amd64 / test-nsys-jax / runner / launch-slurm-runner
amd64  /  ...  /  launch-slurm-runner
27m 34s
amd64 / test-pallas / runner / launch-slurm-runner
amd64  /  ...  /  build-gemma
5m 47s
amd64 / build-gemma / build-gemma
amd64  /  ...  /  build-levanter
4m 34s
amd64 / build-levanter / build-levanter
amd64  /  ...  /  build-maxtext
8m 25s
amd64 / build-maxtext / build-maxtext
amd64  /  ...  /  build-triton
9m 4s
amd64 / build-triton / build-triton
amd64  /  ...  /  build-equinox
3m 24s
amd64 / build-equinox / build-equinox
arm64  /  ...  /  build-upstream-pax
16m 37s
arm64 / build-upstream-pax / build-upstream-pax
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  /  ...  /  build-upstream-t5x
15m 0s
arm64 / build-upstream-t5x / build-upstream-t5x
arm64  /  ...  /  launch-slurm-runner
arm64 / test-jax / runner / launch-slurm-runner
arm64  /  ...  /  launch-slurm-runner
arm64 / test-nsys-jax / runner / launch-slurm-runner
arm64  /  ...  /  launch-slurm-runner
arm64 / test-pallas / runner / launch-slurm-runner
arm64  /  ...  /  build
arm64 / build-gemma / build
arm64  /  ...  /  build-levanter
6m 15s
arm64 / build-levanter / build-levanter
arm64  /  ...  /  build-maxtext
12m 37s
arm64 / build-maxtext / build-maxtext
arm64  /  ...  /  build
arm64 / build-triton / build
arm64  /  ...  /  build-equinox
4m 39s
arm64 / build-equinox / build-equinox
amd64  /  ...  /  build-rosetta
6m 20s
amd64 / build-rosetta-pax / build-rosetta
Matrix: amd64 / test-te / run-unit-test
amd64  /  ...  /  launch-slurm-runner
1h 48m
amd64 / test-te / runner / launch-slurm-runner
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
amd64  /  ...  /  build-rosetta
8m 37s
amd64 / build-rosetta-t5x / build-rosetta
Matrix: amd64 / test-upstream-t5x / t5x-multi-gpu
Matrix: amd64 / test-upstream-t5x / t5x-multi-node
Matrix: amd64 / test-gemma / run-unit-test
amd64  /  ...  /  launch-slurm-runner
28m 6s
amd64 / test-gemma / runner / launch-slurm-runner
Matrix: amd64 / test-levanter / run-unit-test
amd64  /  ...  /  launch-slurm-runner
43m 44s
amd64 / test-levanter / runner / launch-slurm-runner
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
amd64  /  ...  /  launch-slurm-runner
amd64 / test-triton / runner / launch-slurm-runner
arm64  /  ...  /  build-rosetta
8m 47s
arm64 / build-rosetta-pax / build-rosetta
Matrix: arm64 / test-te / run-unit-test
Waiting for pending jobs
arm64  /  ...  /  launch-slurm-runner
arm64 / test-te / runner / 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
arm64  /  ...  /  build-rosetta
12m 55s
arm64 / build-rosetta-t5x / build-rosetta
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
arm64  /  ...  /  launch-slurm-runner
arm64 / test-gemma / runner / launch-slurm-runner
Matrix: arm64 / test-levanter / run-unit-test
Waiting for pending jobs
arm64  /  ...  /  launch-slurm-runner
arm64 / test-levanter / runner / launch-slurm-runner
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
arm64  /  ...  /  launch-slurm-runner
arm64 / test-triton / runner / launch-slurm-runner
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
amd64  /  ...  /  test-upstream-pax-summary
0s
amd64 / test-upstream-pax / test-upstream-pax-summary
amd64  /  ...  /  test-upstream-pax-metrics
22s
amd64 / test-upstream-pax / test-upstream-pax-metrics
amd64  /  ...  /  sitrep
14s
amd64 / test-te-multigpu / sitrep
amd64  /  collect-docker-tags
0s
amd64 / collect-docker-tags
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
amd64  /  ...  /  test-upstream-t5x-summary
0s
amd64 / test-upstream-t5x / test-upstream-t5x-summary
amd64  /  ...  /  test-upstream-t5x-metrics
21s
amd64 / test-upstream-t5x / test-upstream-t5x-metrics
amd64  /  ...  /  test-maxtext-summary
0s
amd64 / test-maxtext / test-maxtext-summary
amd64  /  ...  /  test-maxtext-metrics
22s
amd64 / test-maxtext / test-maxtext-metrics
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
arm64  /  ...  /  test-upstream-pax-summary
arm64 / test-upstream-pax / test-upstream-pax-summary
arm64  /  ...  /  test-upstream-pax-metrics
arm64 / test-upstream-pax / test-upstream-pax-metrics
arm64  /  ...  /  sitrep
arm64 / test-te-multigpu / sitrep
arm64  /  collect-docker-tags
0s
arm64 / collect-docker-tags
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
arm64  /  ...  /  test-upstream-t5x-summary
arm64 / test-upstream-t5x / test-upstream-t5x-summary
arm64  /  ...  /  test-upstream-t5x-metrics
arm64 / test-upstream-t5x / test-upstream-t5x-metrics
arm64  /  ...  /  test-maxtext-summary
arm64 / test-maxtext / test-maxtext-summary
arm64  /  ...  /  test-maxtext-metrics
arm64 / test-maxtext / test-maxtext-metrics
amd64  /  ...  /  test-pax-rosetta-summary
0s
amd64 / test-rosetta-pax / test-pax-rosetta-summary
amd64  /  ...  /  test-pax-rosetta-metrics
23s
amd64 / test-rosetta-pax / test-pax-rosetta-metrics
amd64  /  ...  /  sitrep
18s
amd64 / test-upstream-pax / test-upstream-pax-sitrep / sitrep
amd64  /  ...  /  test-t5x-rosetta-summary
0s
amd64 / test-rosetta-t5x / test-t5x-rosetta-summary
amd64  /  ...  /  test-t5x-rosetta-metrics
15s
amd64 / test-rosetta-t5x / test-t5x-rosetta-metrics
amd64  /  ...  /  sitrep
7s
amd64 / test-upstream-t5x / test-upstream-t5x-sitrep / sitrep
amd64  /  ...  /  sitrep
12s
amd64 / test-maxtext / test-maxtext-sitrep / sitrep
arm64  /  ...  /  test-pax-rosetta-summary
arm64 / test-rosetta-pax / test-pax-rosetta-summary
arm64  /  ...  /  test-pax-rosetta-metrics
arm64 / test-rosetta-pax / test-pax-rosetta-metrics
arm64  /  ...  /  sitrep
arm64 / test-upstream-pax / test-upstream-pax-sitrep / sitrep
arm64  /  ...  /  test-t5x-rosetta-summary
arm64 / test-rosetta-t5x / test-t5x-rosetta-summary
arm64  /  ...  /  test-t5x-rosetta-metrics
arm64 / test-rosetta-t5x / test-t5x-rosetta-metrics
arm64  /  ...  /  sitrep
arm64 / test-upstream-t5x / test-upstream-t5x-sitrep / sitrep
arm64  /  ...  /  sitrep
arm64 / test-maxtext / test-maxtext-sitrep / sitrep
amd64  /  ...  /  sitrep
7s
amd64 / test-rosetta-pax / test-pax-rosetta-sitrep / sitrep
amd64  /  ...  /  test-upstream-pax-outcome
0s
amd64 / test-upstream-pax / test-upstream-pax-outcome
amd64  /  ...  /  sitrep
8s
amd64 / test-rosetta-t5x / test-t5x-rosetta-sitrep / sitrep
amd64  /  ...  /  test-upstream-t5x-outcome
0s
amd64 / test-upstream-t5x / test-upstream-t5x-outcome
amd64  /  ...  /  test-maxtext-outcome
0s
amd64 / test-maxtext / test-maxtext-outcome
arm64  /  ...  /  sitrep
arm64 / test-rosetta-pax / test-pax-rosetta-sitrep / sitrep
arm64  /  ...  /  test-upstream-pax-outcome
arm64 / test-upstream-pax / test-upstream-pax-outcome
arm64  /  ...  /  sitrep
arm64 / test-rosetta-t5x / test-t5x-rosetta-sitrep / sitrep
arm64  /  ...  /  test-upstream-t5x-outcome
arm64 / test-upstream-t5x / test-upstream-t5x-outcome
arm64  /  ...  /  test-maxtext-outcome
arm64 / test-maxtext / test-maxtext-outcome
amd64  /  ...  /  test-pax-rosetta-outcome
0s
amd64 / test-rosetta-pax / test-pax-rosetta-outcome
amd64  /  ...  /  test-t5x-rosetta-outcome
0s
amd64 / test-rosetta-t5x / test-t5x-rosetta-outcome
arm64  /  ...  /  test-pax-rosetta-outcome
arm64 / test-rosetta-pax / test-pax-rosetta-outcome
arm64  /  ...  /  test-t5x-rosetta-outcome
arm64 / test-rosetta-t5x / test-t5x-rosetta-outcome
make-publish-configs
4s
make-publish-configs
merge-new-manifest
13s
merge-new-manifest
Matrix: publish-containers
finalize  /  workflow-badge
4s
finalize / workflow-badge
finalize  /  report
14s
finalize / report
finalize  /  upload-badge
7s
finalize / upload-badge
finalize  /  publish-badge
3s
finalize / publish-badge
Fit to window
Zoom out
Zoom in

Annotations

7 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-gemma / gemma-A100-unit-test
Process completed with exit code 1.
amd64 / test-gemma / gemma-V100-unit-test
Process completed with exit code 1.
amd64 / test-upstream-t5x / test-upstream-t5x-outcome
Process completed with exit code 1.
amd64 / test-rosetta-t5x / test-t5x-rosetta-outcome
Process completed with exit code 1.
amd64 / test-rosetta-pax / test-pax-rosetta-outcome
Process completed with exit code 1.
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
568 Bytes
artifact-base-build-arm64
567 Bytes
artifact-equinox-build-amd64
569 Bytes
artifact-equinox-build-arm64
569 Bytes
artifact-final-report
10.9 KB
artifact-gemma-build-amd64
560 Bytes
artifact-jax-build-amd64
554 Bytes
artifact-jax-build-arm64
553 Bytes
artifact-levanter-build-amd64
571 Bytes
artifact-levanter-build-arm64
574 Bytes
artifact-maxtext-build-amd64
568 Bytes
artifact-maxtext-build-arm64
568 Bytes
artifact-maxtext-test
670 Bytes
artifact-pax-build-amd64
568 Bytes
artifact-pax-build-arm64
567 Bytes
artifact-rosetta-build-pax-amd64
583 Bytes
artifact-rosetta-build-pax-arm64
583 Bytes
artifact-rosetta-build-t5x-amd64
584 Bytes
artifact-rosetta-build-t5x-arm64
585 Bytes
artifact-rosetta-pax-mgmn-test
4.45 KB
artifact-rosetta-t5x-mgmn-test
2.22 KB
artifact-t5x-build-amd64
567 Bytes
artifact-t5x-build-arm64
568 Bytes
artifact-triton-build-amd64
469 Bytes
artifact-upstream-pax-mgmn-test
2.77 KB
artifact-upstream-t5x-mgmn-test
644 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
18.5 KB
jax-unit-test-V100
24 KB
levanter-unit-test-A100
13.9 KB
levanter-unit-test-V100
14.1 KB
mealkit-equinox
269 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
29.3 MB
nsys-jax-unit-test-V100
16 MB
pallas-unit-test-A100
7.62 KB
pallas-unit-test-V100
7.54 KB
rosetta-pax-11700832892-16DP1FSDP1TP1PP_TE
719 KB
rosetta-pax-11700832892-1DP1FSDP1TP1PP_TE
92.5 KB
rosetta-pax-11700832892-1DP2FSDP4TP1PP_single_process_TE
112 KB
rosetta-pax-11700832892-1DP8FSDP1TP1PP_TE
388 KB
rosetta-pax-11700832892-2DP1FSDP1TP4PP
288 KB
rosetta-pax-11700832892-2DP1FSDP2TP4PP
548 KB
rosetta-pax-11700832892-4DP1FSDP2TP1PP
414 KB
rosetta-pax-11700832892-4DP1FSDP2TP1PP_TE
392 KB
rosetta-pax-11700832892-5B_fused_attn_0
424 KB
rosetta-pax-11700832892-5B_fused_attn_1
435 KB
rosetta-pax-11700832892-8DP1FSDP1TP1PP
405 KB
rosetta-pax-11700832892-8DP1FSDP1TP1PP_TE
374 KB
rosetta-pax-11700832892-8DP1FSDP1TP1PP_eval_TE
83.7 KB
rosetta-pax-11700832892-8DP1FSDP1TP1PP_single_process_TE
112 KB
rosetta-pax-11700832892-8DP_TE_dropout
387 KB
rosetta-pax-11700832892-LLaMA_eval_TE
259 KB
rosetta-pax-metrics-test-log
9.98 KB
rosetta-t5x-11700832892-1P1G_te-0
35.1 KB
rosetta-t5x-11700832892-1P8G_te-1
35.1 KB
rosetta-t5x-11700832892-2N2G_te-0
40.3 KB
rosetta-t5x-11700832892-2N8G-te-1
58.6 KB
rosetta-t5x-metrics-test-log
5.63 KB
rosetta-t5x-vit-11700832892-VIT1G1N
21.6 KB
rosetta-t5x-vit-11700832892-VIT1G2N
23.4 KB
rosetta-t5x-vit-11700832892-VIT1P8G
21.8 KB
rosetta-t5x-vit-11700832892-VIT8G1N
32.9 KB
rosetta-t5x-vit-11700832892-VIT8G2N
45.3 KB
te-2GPU
5.34 KB
te-4GPU
5.38 KB
te-8GPU
5.42 KB
te-multigpu-test
525 Bytes
te-unit-test-A100
723 KB
te-unit-test-V100
614 KB
upstream-maxtext-11700832892-1DP1FSDP1TP1PP
14.2 KB
upstream-maxtext-11700832892-1DP1FSDP8TP1PP
20 KB
upstream-maxtext-11700832892-1DP2FSDP4TP1PP_single_process
14.4 KB
upstream-maxtext-11700832892-1DP4FSDP2TP1PP
19.7 KB
upstream-maxtext-11700832892-1DP8FSDP1TP1PP
20.1 KB
upstream-maxtext-11700832892-2DP2FSDP2TP1PP
20.1 KB
upstream-maxtext-11700832892-4DP2FSDP2TP1PP
25.7 KB
upstream-maxtext-metrics-test-log
1.86 KB
upstream-pax-11700832892-16DP1FSDP1TP1PP
848 KB
upstream-pax-11700832892-1DP1FSDP1TP1PP
147 KB
upstream-pax-11700832892-1DP2FSDP4TP1PP_single_process
147 KB
upstream-pax-11700832892-1DP8FSDP1TP1PP
463 KB
upstream-pax-11700832892-2DP1FSDP1TP4PP
326 KB
upstream-pax-11700832892-2DP1FSDP2TP4PP
605 KB
upstream-pax-11700832892-4DP1FSDP2TP1PP
471 KB
upstream-pax-11700832892-8DP1FSDP1TP1PP
465 KB
upstream-pax-11700832892-8DP1FSDP1TP1PP_eval
114 KB
upstream-pax-11700832892-8DP1FSDP1TP1PP_single_process
147 KB
upstream-pax-11700832892-LLaMA_eval
264 KB
upstream-pax-metrics-test-log
7.1 KB
upstream-t5x-11700832892-1P2G_fmha
33.9 KB
upstream-t5x-11700832892-1P8G
33.5 KB
upstream-t5x-11700832892-8G2N
54.3 KB
upstream-t5x-11700832892-8G2N_fmha
54.9 KB
upstream-t5x-metrics-test-log
4.51 KB