Skip to content

Model XLA Flags

Model XLA Flags #3329

Triggered via pull request September 20, 2024 17:11
Status Failure
Total duration 4h 15m 12s
Artifacts 118

ci.yaml

on: pull_request
metadata
0s
metadata
bump-manifest
17s
bump-manifest
Matrix: amd64 / test-distribution
Matrix: arm64 / test-distribution
amd64  /  ...  /  build-base
4m 28s
amd64 / build-base / build-base
arm64  /  ...  /  build-base
4m 49s
arm64 / build-base / build-base
amd64  /  ...  /  build-jax
17m 42s
amd64 / build-jax / build-jax
arm64  /  ...  /  build-jax
29m 27s
arm64 / build-jax / build-jax
amd64  /  ...  /  build-upstream-pax
6m 18s
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 38s
amd64 / build-upstream-t5x / build-upstream-t5x
amd64  /  ...  /  launch-slurm-runner
10m 25s
amd64 / test-jax / runner / launch-slurm-runner
amd64  /  ...  /  launch-slurm-runner
16m 49s
amd64 / test-nsys-jax / runner / launch-slurm-runner
amd64  /  ...  /  launch-slurm-runner
13m 40s
amd64 / test-pallas / runner / launch-slurm-runner
amd64  /  ...  /  build-gemma
5m 33s
amd64 / build-gemma / build-gemma
amd64  /  ...  /  build-levanter
4m 17s
amd64 / build-levanter / build-levanter
amd64  /  ...  /  build-maxtext
7m 35s
amd64 / build-maxtext / build-maxtext
amd64  /  ...  /  build-triton
11m 16s
amd64 / build-triton / build-triton
amd64  /  ...  /  build-equinox
3m 36s
amd64 / build-equinox / build-equinox
arm64  /  ...  /  build-upstream-pax
31m 4s
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
23m 58s
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
11m 22s
arm64 / build-levanter / build-levanter
arm64  /  ...  /  build-maxtext
22m 42s
arm64 / build-maxtext / build-maxtext
arm64  /  ...  /  build
arm64 / build-triton / build
arm64  /  ...  /  build-equinox
9m 29s
arm64 / build-equinox / build-equinox
amd64  /  ...  /  build-rosetta
6m 43s
amd64 / build-rosetta-pax / build-rosetta
Matrix: amd64 / test-te / run-unit-test
amd64  /  ...  /  launch-slurm-runner
1h 17m
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 5s
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
17m 8s
amd64 / test-gemma / runner / launch-slurm-runner
Matrix: amd64 / test-levanter / run-unit-test
amd64  /  ...  /  launch-slurm-runner
30m 16s
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 3m
amd64 / test-triton / runner / launch-slurm-runner
arm64  /  ...  /  build-rosetta
16m 59s
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
20m 4s
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
8s
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
14s
amd64 / test-upstream-t5x / test-upstream-t5x-metrics
amd64  /  ...  /  test-maxtext-summary
0s
amd64 / test-maxtext / test-maxtext-summary
amd64  /  ...  /  test-maxtext-metrics
16s
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
6s
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
27s
amd64 / test-rosetta-t5x / test-t5x-rosetta-metrics
amd64  /  ...  /  sitrep
8s
amd64 / test-upstream-t5x / test-upstream-t5x-sitrep / sitrep
amd64  /  ...  /  sitrep
7s
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
13s
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
10s
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
0s
merge-new-manifest
Matrix: publish-containers
finalize  /  workflow-badge
3s
finalize / workflow-badge
finalize  /  report
24s
finalize / report
finalize  /  upload-badge
7s
finalize / upload-badge
finalize  /  publish-badge
4s
finalize / publish-badge
Fit to window
Zoom out
Zoom in

Annotations

6 errors
amd64 / test-te / te-A100-unit-test
The self-hosted runner: A100-273212e616d6 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-pax / test-upstream-pax-outcome
Process completed with exit code 1.
amd64 / test-upstream-t5x / test-upstream-t5x-outcome
Process completed with exit code 1.
amd64 / test-maxtext / test-maxtext-outcome
Process completed with exit code 1.
amd64 / test-rosetta-pax / test-pax-rosetta-outcome
Process completed with exit code 1.
amd64 / test-rosetta-t5x / test-t5x-rosetta-outcome
Process completed with exit code 1.

Artifacts

Produced during runtime
Name Size
artifact-base-build-amd64
568 Bytes
artifact-base-build-arm64
566 Bytes
artifact-equinox-build-amd64
569 Bytes
artifact-equinox-build-arm64
568 Bytes
artifact-final-report
13.4 KB
artifact-gemma-build-amd64
560 Bytes
artifact-jax-build-amd64
554 Bytes
artifact-jax-build-arm64
554 Bytes
artifact-levanter-build-amd64
572 Bytes
artifact-levanter-build-arm64
572 Bytes
artifact-maxtext-build-amd64
568 Bytes
artifact-maxtext-build-arm64
568 Bytes
artifact-maxtext-test
675 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
582 Bytes
artifact-rosetta-build-t5x-amd64
584 Bytes
artifact-rosetta-build-t5x-arm64
585 Bytes
artifact-rosetta-pax-mgmn-test
4.94 KB
artifact-rosetta-t5x-mgmn-test
3.26 KB
artifact-t5x-build-amd64
569 Bytes
artifact-t5x-build-arm64
568 Bytes
artifact-triton-build-amd64
562 Bytes
artifact-upstream-pax-mgmn-test
2.8 KB
artifact-upstream-t5x-mgmn-test
2.12 KB
artifact-workflow-metadata
277 Bytes
bumped-manifest
71.2 KB
final-base
254 Bytes
final-equinox
263 Bytes
final-gemma
257 Bytes
final-jax
251 Bytes
final-levanter
266 Bytes
final-maxtext
262 Bytes
final-pax
251 Bytes
final-t5x
251 Bytes
final-triton
259 Bytes
final-upstream-pax
276 Bytes
final-upstream-t5x
276 Bytes
gemma-unit-test-A100
4.09 KB
gemma-unit-test-V100
2.74 KB
jax-unit-test-A100
17.3 KB
jax-unit-test-V100
17.6 KB
levanter-unit-test-A100
14.5 KB
levanter-unit-test-V100
13.9 KB
mealkit-equinox
272 Bytes
mealkit-gemma
266 Bytes
mealkit-jax
261 Bytes
mealkit-levanter
275 Bytes
mealkit-maxtext
271 Bytes
mealkit-pax
260 Bytes
mealkit-t5x
262 Bytes
mealkit-triton
268 Bytes
mealkit-upstream-pax
285 Bytes
mealkit-upstream-t5x
286 Bytes
nsys-jax-unit-test-A100
31.4 MB
nsys-jax-unit-test-V100
16.3 MB
pallas-unit-test-A100
7.34 KB
pallas-unit-test-V100
7.19 KB
rosetta-pax-10963449920-16DP1FSDP1TP1PP_TE
618 KB
rosetta-pax-10963449920-1DP1FSDP1TP1PP_TE
86.7 KB
rosetta-pax-10963449920-1DP2FSDP4TP1PP_single_process_TE
105 KB
rosetta-pax-10963449920-1DP8FSDP1TP1PP_TE
330 KB
rosetta-pax-10963449920-2DP1FSDP1TP4PP
268 KB
rosetta-pax-10963449920-2DP1FSDP2TP4PP
496 KB
rosetta-pax-10963449920-4DP1FSDP2TP1PP
370 KB
rosetta-pax-10963449920-4DP1FSDP2TP1PP_TE
330 KB
rosetta-pax-10963449920-5B_fused_attn_0
388 KB
rosetta-pax-10963449920-5B_fused_attn_1
394 KB
rosetta-pax-10963449920-8DP1FSDP1TP1PP
362 KB
rosetta-pax-10963449920-8DP1FSDP1TP1PP_TE
329 KB
rosetta-pax-10963449920-8DP1FSDP1TP1PP_eval_TE
77.6 KB
rosetta-pax-10963449920-8DP1FSDP1TP1PP_single_process_TE
105 KB
rosetta-pax-10963449920-8DP_TE_dropout
329 KB
rosetta-pax-10963449920-LLaMA_eval_TE
224 KB
rosetta-pax-metrics-test-log
10.2 KB
rosetta-t5x-10963449920-1P1G_te-0
4.43 MB
rosetta-t5x-10963449920-1P8G_te-1
4.63 MB
rosetta-t5x-10963449920-2N2G_te-0
4.56 MB
rosetta-t5x-10963449920-2N8G-te-1
4.68 MB
rosetta-t5x-metrics-test-log
7.63 KB
rosetta-t5x-vit-10963449920-VIT1G1N
21.7 KB
rosetta-t5x-vit-10963449920-VIT1G2N
23.5 KB
rosetta-t5x-vit-10963449920-VIT1P8G
22.1 KB
rosetta-t5x-vit-10963449920-VIT8G1N
33.5 KB
rosetta-t5x-vit-10963449920-VIT8G2N
46.1 KB
te-2GPU
5.28 KB
te-4GPU
5.33 KB
te-8GPU
5.37 KB
te-multigpu-test
525 Bytes
te-unit-test-V100
626 KB
triton-unit-test-A100
4.8 KB
triton-unit-test-V100
4.87 KB
upstream-maxtext-10963449920-1DP1FSDP1TP1PP
13.6 KB
upstream-maxtext-10963449920-1DP1FSDP8TP1PP
16.6 KB
upstream-maxtext-10963449920-1DP2FSDP4TP1PP_single_process
13.8 KB
upstream-maxtext-10963449920-1DP4FSDP2TP1PP
19 KB
upstream-maxtext-10963449920-1DP8FSDP1TP1PP
19 KB
upstream-maxtext-10963449920-2DP2FSDP2TP1PP
18.9 KB
upstream-maxtext-10963449920-4DP2FSDP2TP1PP
24.7 KB
upstream-maxtext-metrics-test-log
3 KB
upstream-pax-10963449920-16DP1FSDP1TP1PP
776 KB
upstream-pax-10963449920-1DP1FSDP1TP1PP
141 KB
upstream-pax-10963449920-1DP2FSDP4TP1PP_single_process
142 KB
upstream-pax-10963449920-1DP8FSDP1TP1PP
410 KB
upstream-pax-10963449920-2DP1FSDP1TP4PP
296 KB
upstream-pax-10963449920-2DP1FSDP2TP4PP
548 KB
upstream-pax-10963449920-4DP1FSDP2TP1PP
418 KB
upstream-pax-10963449920-8DP1FSDP1TP1PP
423 KB
upstream-pax-10963449920-8DP1FSDP1TP1PP_eval
108 KB
upstream-pax-10963449920-8DP1FSDP1TP1PP_single_process
142 KB
upstream-pax-10963449920-LLaMA_eval
237 KB
upstream-pax-metrics-test-log
7.11 KB
upstream-t5x-10963449920-1P2G_fmha
5.02 MB
upstream-t5x-10963449920-1P8G
5.11 MB
upstream-t5x-10963449920-8G2N
5.22 MB
upstream-t5x-10963449920-8G2N_fmha
5.14 MB
upstream-t5x-metrics-test-log
8.62 KB