Skip to content

CI

CI #3489

Triggered via schedule October 31, 2024 09:32
Status Failure
Total duration 10h 58m 51s
Artifacts 118

ci.yaml

on: schedule
metadata
0s
metadata
bump-manifest
36s
bump-manifest
Matrix: amd64 / test-distribution
Matrix: arm64 / test-distribution
amd64  /  ...  /  build-base
3m 54s
amd64 / build-base / build-base
arm64  /  ...  /  build-base
4m 40s
arm64 / build-base / build-base
amd64  /  ...  /  build-jax
8m 15s
amd64 / build-jax / build-jax
arm64  /  ...  /  build-jax
14m 55s
arm64 / build-jax / build-jax
amd64  /  ...  /  build-upstream-pax
6m 35s
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 23s
amd64 / build-upstream-t5x / build-upstream-t5x
amd64  /  ...  /  launch-slurm-runner
2h 32m
amd64 / test-jax / runner / launch-slurm-runner
amd64  /  ...  /  launch-slurm-runner
2h 34m
amd64 / test-nsys-jax / runner / launch-slurm-runner
amd64  /  ...  /  launch-slurm-runner
2h 25m
amd64 / test-pallas / runner / launch-slurm-runner
amd64  /  ...  /  build-gemma
5m 40s
amd64 / build-gemma / build-gemma
amd64  /  ...  /  build-levanter
4m 39s
amd64 / build-levanter / build-levanter
amd64  /  ...  /  build-maxtext
6m 23s
amd64 / build-maxtext / build-maxtext
amd64  /  ...  /  build-triton
11m 19s
amd64 / build-triton / build-triton
amd64  /  ...  /  build-equinox
3m 46s
amd64 / build-equinox / build-equinox
arm64  /  ...  /  build-upstream-pax
17m 10s
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
19m 8s
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 28s
arm64 / build-levanter / build-levanter
arm64  /  ...  /  build-maxtext
17m 24s
arm64 / build-maxtext / build-maxtext
arm64  /  ...  /  build
arm64 / build-triton / build
arm64  /  ...  /  build-equinox
4m 29s
arm64 / build-equinox / build-equinox
amd64  /  ...  /  build-rosetta
6m 36s
amd64 / build-rosetta-pax / build-rosetta
Matrix: amd64 / test-te / run-unit-test
amd64  /  ...  /  launch-slurm-runner
2h 46m
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 4s
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
3h 36m
amd64 / test-gemma / runner / launch-slurm-runner
Matrix: amd64 / test-levanter / run-unit-test
amd64  /  ...  /  launch-slurm-runner
2h 25m
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
amd64  /  ...  /  launch-slurm-runner
2h 47m
amd64 / test-triton / runner / launch-slurm-runner
arm64  /  ...  /  build-rosetta
8m 40s
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
13m 7s
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
16s
amd64 / test-upstream-pax / test-upstream-pax-metrics
amd64  /  ...  /  sitrep
6s
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
15s
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
17s
amd64 / test-rosetta-pax / test-pax-rosetta-metrics
amd64  /  ...  /  sitrep
9s
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
20s
amd64 / test-rosetta-t5x / test-t5x-rosetta-metrics
amd64  /  ...  /  sitrep
13s
amd64 / test-upstream-t5x / test-upstream-t5x-sitrep / sitrep
amd64  /  ...  /  sitrep
6s
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
8s
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
13s
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
3s
make-publish-configs
merge-new-manifest
9s
merge-new-manifest
Matrix: publish-containers
finalize  /  workflow-badge
4s
finalize / workflow-badge
finalize  /  report
14s
finalize / report
finalize  /  upload-badge
5s
finalize / upload-badge
finalize  /  publish-badge
5s
finalize / publish-badge
Fit to window
Zoom out
Zoom in

Annotations

7 errors and 2 warnings
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-te / te-A100-unit-test
The self-hosted runner: A100-5326092f754b lost communication with the server. Verify the machine is running and has a healthy network connection. Anything in your workflow that terminates the runner process, starves it for CPU/Memory, or blocks its network access can cause this error.
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-upstream-pax / test-upstream-pax-outcome
Process completed with exit code 1.
amd64 / test-rosetta-pax / test-pax-rosetta-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 Expired
567 Bytes
artifact-base-build-arm64 Expired
569 Bytes
artifact-equinox-build-amd64 Expired
570 Bytes
artifact-equinox-build-arm64 Expired
568 Bytes
artifact-final-report Expired
10.7 KB
artifact-gemma-build-amd64 Expired
560 Bytes
artifact-jax-build-amd64 Expired
554 Bytes
artifact-jax-build-arm64 Expired
554 Bytes
artifact-levanter-build-amd64 Expired
572 Bytes
artifact-levanter-build-arm64 Expired
572 Bytes
artifact-maxtext-build-amd64 Expired
568 Bytes
artifact-maxtext-build-arm64 Expired
567 Bytes
artifact-maxtext-test Expired
670 Bytes
artifact-pax-build-amd64 Expired
567 Bytes
artifact-pax-build-arm64 Expired
567 Bytes
artifact-rosetta-build-pax-amd64 Expired
583 Bytes
artifact-rosetta-build-pax-arm64 Expired
583 Bytes
artifact-rosetta-build-t5x-amd64 Expired
584 Bytes
artifact-rosetta-build-t5x-arm64 Expired
584 Bytes
artifact-rosetta-pax-mgmn-test Expired
4.01 KB
artifact-rosetta-t5x-mgmn-test Expired
2.2 KB
artifact-t5x-build-amd64 Expired
568 Bytes
artifact-t5x-build-arm64 Expired
568 Bytes
artifact-triton-build-amd64 Expired
564 Bytes
artifact-upstream-pax-mgmn-test Expired
2.79 KB
artifact-upstream-t5x-mgmn-test Expired
644 Bytes
artifact-workflow-metadata Expired
277 Bytes
bumped-manifest Expired
71.8 KB
final-base Expired
249 Bytes
final-equinox Expired
258 Bytes
final-gemma Expired
252 Bytes
final-jax Expired
246 Bytes
final-levanter Expired
261 Bytes
final-maxtext Expired
258 Bytes
final-pax Expired
246 Bytes
final-t5x Expired
246 Bytes
final-triton Expired
255 Bytes
final-upstream-pax Expired
273 Bytes
final-upstream-t5x Expired
273 Bytes
gemma-unit-test-A100 Expired
1.93 KB
gemma-unit-test-V100 Expired
1.93 KB
jax-unit-test-A100 Expired
18.1 KB
jax-unit-test-V100 Expired
23.4 KB
levanter-unit-test-A100 Expired
12.7 KB
levanter-unit-test-V100 Expired
13.2 KB
mealkit-equinox Expired
270 Bytes
mealkit-gemma Expired
263 Bytes
mealkit-jax Expired
256 Bytes
mealkit-levanter Expired
272 Bytes
mealkit-maxtext Expired
269 Bytes
mealkit-pax Expired
258 Bytes
mealkit-t5x Expired
258 Bytes
mealkit-triton Expired
266 Bytes
mealkit-upstream-pax Expired
283 Bytes
mealkit-upstream-t5x Expired
283 Bytes
nsys-jax-unit-test-A100 Expired
30.2 MB
nsys-jax-unit-test-V100 Expired
15.9 MB
pallas-unit-test-A100 Expired
14.4 KB
pallas-unit-test-V100 Expired
7.43 KB
rosetta-pax-11609421131-16DP1FSDP1TP1PP_TE Expired
633 KB
rosetta-pax-11609421131-1DP1FSDP1TP1PP_TE Expired
87.4 KB
rosetta-pax-11609421131-1DP2FSDP4TP1PP_single_process_TE Expired
62.7 KB
rosetta-pax-11609421131-1DP8FSDP1TP1PP_TE Expired
332 KB
rosetta-pax-11609421131-2DP1FSDP1TP4PP Expired
270 KB
rosetta-pax-11609421131-2DP1FSDP2TP4PP Expired
507 KB
rosetta-pax-11609421131-4DP1FSDP2TP1PP Expired
363 KB
rosetta-pax-11609421131-4DP1FSDP2TP1PP_TE Expired
337 KB
rosetta-pax-11609421131-5B_fused_attn_0 Expired
391 KB
rosetta-pax-11609421131-5B_fused_attn_1 Expired
396 KB
rosetta-pax-11609421131-8DP1FSDP1TP1PP Expired
376 KB
rosetta-pax-11609421131-8DP1FSDP1TP1PP_TE Expired
339 KB
rosetta-pax-11609421131-8DP1FSDP1TP1PP_eval_TE Expired
75.8 KB
rosetta-pax-11609421131-8DP1FSDP1TP1PP_single_process_TE Expired
62.8 KB
rosetta-pax-11609421131-8DP_TE_dropout Expired
345 KB
rosetta-pax-11609421131-LLaMA_eval_TE Expired
233 KB
rosetta-pax-metrics-test-log Expired
9.82 KB
rosetta-t5x-11609421131-1P1G_te-0 Expired
35.2 KB
rosetta-t5x-11609421131-1P8G_te-1 Expired
35.2 KB
rosetta-t5x-11609421131-2N2G_te-0 Expired
40.4 KB
rosetta-t5x-11609421131-2N8G-te-1 Expired
59.3 KB
rosetta-t5x-metrics-test-log Expired
5.6 KB
rosetta-t5x-vit-11609421131-VIT1G1N Expired
21.8 KB
rosetta-t5x-vit-11609421131-VIT1G2N Expired
24 KB
rosetta-t5x-vit-11609421131-VIT1P8G Expired
22.2 KB
rosetta-t5x-vit-11609421131-VIT8G1N Expired
34 KB
rosetta-t5x-vit-11609421131-VIT8G2N Expired
47.9 KB
te-2GPU Expired
7.16 KB
te-4GPU Expired
7.18 KB
te-8GPU Expired
7.25 KB
te-multigpu-test Expired
525 Bytes
te-unit-test-V100 Expired
682 KB
triton-unit-test-A100 Expired
7.52 KB
triton-unit-test-V100 Expired
7.57 KB
upstream-maxtext-11609421131-1DP1FSDP1TP1PP Expired
14.3 KB
upstream-maxtext-11609421131-1DP1FSDP8TP1PP Expired
20.6 KB
upstream-maxtext-11609421131-1DP2FSDP4TP1PP_single_process Expired
14.6 KB
upstream-maxtext-11609421131-1DP4FSDP2TP1PP Expired
20.6 KB
upstream-maxtext-11609421131-1DP8FSDP1TP1PP Expired
20.7 KB
upstream-maxtext-11609421131-2DP2FSDP2TP1PP Expired
20.8 KB
upstream-maxtext-11609421131-4DP2FSDP2TP1PP Expired
27.2 KB
upstream-maxtext-metrics-test-log Expired
1.88 KB
upstream-pax-11609421131-16DP1FSDP1TP1PP Expired
794 KB
upstream-pax-11609421131-1DP1FSDP1TP1PP Expired
141 KB
upstream-pax-11609421131-1DP2FSDP4TP1PP_single_process Expired
142 KB
upstream-pax-11609421131-1DP8FSDP1TP1PP Expired
428 KB
upstream-pax-11609421131-2DP1FSDP1TP4PP Expired
296 KB
upstream-pax-11609421131-2DP1FSDP2TP4PP Expired
559 KB
upstream-pax-11609421131-4DP1FSDP2TP1PP Expired
422 KB
upstream-pax-11609421131-8DP1FSDP1TP1PP Expired
421 KB
upstream-pax-11609421131-8DP1FSDP1TP1PP_eval Expired
109 KB
upstream-pax-11609421131-8DP1FSDP1TP1PP_single_process Expired
142 KB
upstream-pax-11609421131-LLaMA_eval Expired
245 KB
upstream-pax-metrics-test-log Expired
7.11 KB
upstream-t5x-11609421131-1P2G_fmha Expired
34 KB
upstream-t5x-11609421131-1P8G Expired
33.6 KB
upstream-t5x-11609421131-8G2N Expired
55.5 KB
upstream-t5x-11609421131-8G2N_fmha Expired
55.1 KB
upstream-t5x-metrics-test-log Expired
4.51 KB