Added model support to test-maxtext.sh #3168
kocchopci.yaml
on: pull_request
metadata
0s
Matrix: amd64 / test-distribution
Matrix: arm64 / test-distribution
Matrix: amd64 / test-jax / run-unit-test
Matrix: amd64 / test-pallas / run-unit-test
amd64
/
...
/
launch-slurm-runner
11m 5s
amd64
/
...
/
launch-slurm-runner
4m 58s
Matrix: arm64 / test-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
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
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
Waiting for pending jobs
Matrix: amd64 / test-rosetta-t5x / single-process-multi-device
Waiting for pending jobs
Matrix: amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node
Waiting for pending jobs
Matrix: amd64 / test-rosetta-t5x / vit-single-process-multi-device
Waiting for pending jobs
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
13 errors
|
amd64 / build-rosetta-t5x / build-rosetta
buildx failed with: ERROR: failed to solve: process "/bin/sh -c <<\"EOF\" bash -exu\nMANIFEST_DIR=$(dirname ${MANIFEST_FILE})\nif [[ \"${UPDATE_PATCHES}\" != \"true\" && \"${UPDATE_PATCHES}\" != \"false\" ]]; then\n echo \"UPDATE_PATCHES can only be true or false\"\n exit 1\nfi\nif [[ \"${UPDATE_PATCHES}\" == \"true\" ]]; then\n cp -r /mnt/jax-toolbox/.github/container/patches ${MANIFEST_DIR}/\n cp /mnt/jax-toolbox/.github/container/manifest.yaml ${MANIFEST_DIR}/manifest.yaml\n cp /mnt/jax-toolbox/.github/container/create-distribution.sh ${MANIFEST_DIR}/create-distribution.sh\n # TODO: remove\n cp /mnt/jax-toolbox/.github/container/pip-finalize.sh /usr/local/bin/\nfi\ncp -r /mnt/jax-toolbox/rosetta /opt/rosetta\n\nif [[ -n \"${UPDATED_TE_REF}\" ]]; then\n TE_INSTALL_DIR=/opt/transformer-engine\n yq e \".transformer-engine.latest_verified_commit = \\\"${UPDATED_TE_REF}\\\"\" -i $MANIFEST_FILE\n # Install from source instead of pre-built wheel\n sed -i -E 's@( file:///opt/transformer-engine)/dist/[^ ]*@\\1@' /opt/pip-tools.d/requirements-te.in\n git -C $TE_INSTALL_DIR fetch -a\n if [[ \"${UPDATED_TE_REF}\" =~ ^pull/ ]]; then\n PR_ID=$(cut -d/ -f2 <<<\"${UPDATED_TE_REF}\")\n git -C $TE_INSTALL_DIR fetch origin ${UPDATED_TE_REF}:PR-${PR_ID}\n git -C $TE_INSTALL_DIR checkout PR-${PR_ID}\n else\n git -C $TE_INSTALL_DIR checkout ${UPDATED_TE_REF}\n fi\nfi\n\n# Setting the username/email is required to author commits from patches\ngit config --global user.email \"${GIT_USER_EMAIL}\"\ngit config --global user.name \"${GIT_USER_NAME}\"\n\nbash ${MANIFEST_DIR}/create-distribution.sh \\\n --manifest ${MANIFEST_FILE} \\\n --package t5x\nbash ${MANIFEST_DIR}/create-distribution.sh \\\n --manifest ${MANIFEST_FILE} \\\n --package flax\n# Remove .gitconfig to avoid end-user authoring commits as the \"build user\"\nrm -f ~/.gitconfig\n\necho \"--extra-index-url https://developer.download.nvidia.com/compute/redist\" >> /opt/pip-tools.d/requirements-t5x.in\necho \"-e file:///opt/rosetta\" >> /opt/pip-tools.d/requirements-t5x.in\nEOF" did not complete successfully: exit code: 1
|
|
amd64 / test-jax / jax-A100-unit-test
Process completed with exit code 1.
|
|
amd64 / test-jax / jax-V100-unit-test
Process completed with exit code 1.
|
|
amd64 / test-triton / triton-V100-unit-test
Process completed with exit code 1.
|
|
amd64 / test-maxtext / test-maxtext-outcome
Process completed with exit code 1.
|
|
arm64 / build-rosetta-t5x / build-rosetta
buildx failed with: ERROR: failed to solve: process "/bin/sh -c <<\"EOF\" bash -exu\nMANIFEST_DIR=$(dirname ${MANIFEST_FILE})\nif [[ \"${UPDATE_PATCHES}\" != \"true\" && \"${UPDATE_PATCHES}\" != \"false\" ]]; then\n echo \"UPDATE_PATCHES can only be true or false\"\n exit 1\nfi\nif [[ \"${UPDATE_PATCHES}\" == \"true\" ]]; then\n cp -r /mnt/jax-toolbox/.github/container/patches ${MANIFEST_DIR}/\n cp /mnt/jax-toolbox/.github/container/manifest.yaml ${MANIFEST_DIR}/manifest.yaml\n cp /mnt/jax-toolbox/.github/container/create-distribution.sh ${MANIFEST_DIR}/create-distribution.sh\n # TODO: remove\n cp /mnt/jax-toolbox/.github/container/pip-finalize.sh /usr/local/bin/\nfi\ncp -r /mnt/jax-toolbox/rosetta /opt/rosetta\n\nif [[ -n \"${UPDATED_TE_REF}\" ]]; then\n TE_INSTALL_DIR=/opt/transformer-engine\n yq e \".transformer-engine.latest_verified_commit = \\\"${UPDATED_TE_REF}\\\"\" -i $MANIFEST_FILE\n # Install from source instead of pre-built wheel\n sed -i -E 's@( file:///opt/transformer-engine)/dist/[^ ]*@\\1@' /opt/pip-tools.d/requirements-te.in\n git -C $TE_INSTALL_DIR fetch -a\n if [[ \"${UPDATED_TE_REF}\" =~ ^pull/ ]]; then\n PR_ID=$(cut -d/ -f2 <<<\"${UPDATED_TE_REF}\")\n git -C $TE_INSTALL_DIR fetch origin ${UPDATED_TE_REF}:PR-${PR_ID}\n git -C $TE_INSTALL_DIR checkout PR-${PR_ID}\n else\n git -C $TE_INSTALL_DIR checkout ${UPDATED_TE_REF}\n fi\nfi\n\n# Setting the username/email is required to author commits from patches\ngit config --global user.email \"${GIT_USER_EMAIL}\"\ngit config --global user.name \"${GIT_USER_NAME}\"\n\nbash ${MANIFEST_DIR}/create-distribution.sh \\\n --manifest ${MANIFEST_FILE} \\\n --package t5x\nbash ${MANIFEST_DIR}/create-distribution.sh \\\n --manifest ${MANIFEST_FILE} \\\n --package flax\n# Remove .gitconfig to avoid end-user authoring commits as the \"build user\"\nrm -f ~/.gitconfig\n\necho \"--extra-index-url https://developer.download.nvidia.com/compute/redist\" >> /opt/pip-tools.d/requirements-t5x.in\necho \"-e file:///opt/rosetta\" >> /opt/pip-tools.d/requirements-t5x.in\nEOF" did not complete successfully: exit code: 1
|
|
amd64 / test-te-multigpu / te-multi-gpu (2) / te-2GPU
Process completed with exit code 1.
|
|
amd64 / test-te-multigpu / te-multi-gpu (4) / te-4GPU
Process completed with exit code 1.
|
|
amd64 / test-te-multigpu / te-multi-gpu (8) / te-8GPU
Process completed with exit code 1.
|
|
amd64 / test-upstream-pax / test-upstream-pax-outcome
Process completed with exit code 1.
|
|
amd64 / test-triton / triton-A100-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-pax / test-pax-rosetta-outcome
Process completed with exit code 1.
|
Artifacts
Produced during runtime
| Name | Size | |
|---|---|---|
|
artifact-base-build-amd64
Expired
|
567 Bytes |
|
|
artifact-base-build-arm64
Expired
|
566 Bytes |
|
|
artifact-equinox-build-amd64
Expired
|
571 Bytes |
|
|
artifact-equinox-build-arm64
Expired
|
568 Bytes |
|
|
artifact-final-report
Expired
|
5.56 KB |
|
|
artifact-gemma-build-amd64
Expired
|
561 Bytes |
|
|
artifact-grok-build-amd64
Expired
|
558 Bytes |
|
|
artifact-grok-build-arm64
Expired
|
558 Bytes |
|
|
artifact-jax-build-amd64
Expired
|
553 Bytes |
|
|
artifact-jax-build-arm64
Expired
|
554 Bytes |
|
|
artifact-levanter-build-amd64
Expired
|
572 Bytes |
|
|
artifact-levanter-build-arm64
Expired
|
573 Bytes |
|
|
artifact-maxtext-build-amd64
Expired
|
567 Bytes |
|
|
artifact-maxtext-build-arm64
Expired
|
568 Bytes |
|
|
artifact-maxtext-test
Expired
|
1.22 KB |
|
|
artifact-pax-build-amd64
Expired
|
567 Bytes |
|
|
artifact-pax-build-arm64
Expired
|
568 Bytes |
|
|
artifact-rosetta-build-pax-amd64
Expired
|
582 Bytes |
|
|
artifact-rosetta-build-pax-arm64
Expired
|
584 Bytes |
|
|
artifact-rosetta-build-t5x-amd64
Expired
|
489 Bytes |
|
|
artifact-rosetta-build-t5x-arm64
Expired
|
489 Bytes |
|
|
artifact-rosetta-pax-mgmn-test
Expired
|
730 Bytes |
|
|
artifact-t5x-build-amd64
Expired
|
568 Bytes |
|
|
artifact-t5x-build-arm64
Expired
|
567 Bytes |
|
|
artifact-triton-build-amd64
Expired
|
565 Bytes |
|
|
artifact-upstream-pax-mgmn-test
Expired
|
707 Bytes |
|
|
artifact-upstream-t5x-mgmn-test
Expired
|
657 Bytes |
|
|
artifact-workflow-metadata
Expired
|
278 Bytes |
|
|
bumped-manifest
Expired
|
71.5 KB |
|
|
final-base
Expired
|
254 Bytes |
|
|
final-equinox
Expired
|
263 Bytes |
|
|
final-gemma
Expired
|
257 Bytes |
|
|
final-grok
Expired
|
254 Bytes |
|
|
final-jax
Expired
|
251 Bytes |
|
|
final-levanter
Expired
|
266 Bytes |
|
|
final-maxtext
Expired
|
263 Bytes |
|
|
final-pax
Expired
|
251 Bytes |
|
|
final-triton
Expired
|
260 Bytes |
|
|
final-upstream-pax
Expired
|
276 Bytes |
|
|
final-upstream-t5x
Expired
|
277 Bytes |
|
|
gemma-unit-test-A100
Expired
|
2.88 KB |
|
|
gemma-unit-test-V100
Expired
|
2.88 KB |
|
|
jax-unit-test-A100
Expired
|
3.9 MB |
|
|
jax-unit-test-V100
Expired
|
3.92 MB |
|
|
levanter-unit-test-A100
Expired
|
9.39 KB |
|
|
levanter-unit-test-V100
Expired
|
11.1 KB |
|
|
mealkit-equinox
Expired
|
273 Bytes |
|
|
mealkit-gemma
Expired
|
266 Bytes |
|
|
mealkit-grok
Expired
|
263 Bytes |
|
|
mealkit-jax
Expired
|
261 Bytes |
|
|
mealkit-levanter
Expired
|
275 Bytes |
|
|
mealkit-maxtext
Expired
|
271 Bytes |
|
|
mealkit-pax
Expired
|
262 Bytes |
|
|
mealkit-triton
Expired
|
268 Bytes |
|
|
mealkit-upstream-pax
Expired
|
286 Bytes |
|
|
mealkit-upstream-t5x
Expired
|
286 Bytes |
|
|
pallas-unit-test-A100
Expired
|
7.48 KB |
|
|
pallas-unit-test-V100
Expired
|
7.43 KB |
|
|
rosetta-pax-10205769219-16DP1FSDP1TP1PP_TE
Expired
|
242 KB |
|
|
rosetta-pax-10205769219-1DP1FSDP1TP1PP_TE
Expired
|
59.6 KB |
|
|
rosetta-pax-10205769219-1DP2FSDP4TP1PP_single_process_TE
Expired
|
28 KB |
|
|
rosetta-pax-10205769219-1DP8FSDP1TP1PP_TE
Expired
|
130 KB |
|
|
rosetta-pax-10205769219-2DP1FSDP1TP4PP
Expired
|
129 KB |
|
|
rosetta-pax-10205769219-2DP1FSDP2TP4PP
Expired
|
248 KB |
|
|
rosetta-pax-10205769219-4DP1FSDP2TP1PP
Expired
|
129 KB |
|
|
rosetta-pax-10205769219-4DP1FSDP2TP1PP_TE
Expired
|
129 KB |
|
|
rosetta-pax-10205769219-5B_fused_attn_0
Expired
|
131 KB |
|
|
rosetta-pax-10205769219-5B_fused_attn_1
Expired
|
130 KB |
|
|
rosetta-pax-10205769219-8DP1FSDP1TP1PP
Expired
|
128 KB |
|
|
rosetta-pax-10205769219-8DP1FSDP1TP1PP_TE
Expired
|
126 KB |
|
|
rosetta-pax-10205769219-8DP1FSDP1TP1PP_eval_TE
Expired
|
27.8 KB |
|
|
rosetta-pax-10205769219-8DP1FSDP1TP1PP_single_process_TE
Expired
|
27.9 KB |
|
|
rosetta-pax-10205769219-8DP_TE_dropout
Expired
|
117 KB |
|
|
rosetta-pax-10205769219-LLaMA_eval_TE
Expired
|
119 KB |
|
|
rosetta-pax-metrics-test-log
Expired
|
5.87 KB |
|
|
te-2GPU
Expired
|
13.6 KB |
|
|
te-4GPU
Expired
|
13.6 KB |
|
|
te-8GPU
Expired
|
13.7 KB |
|
|
te-multigpu-test
Expired
|
528 Bytes |
|
|
te-unit-test-A100
Expired
|
969 KB |
|
|
te-unit-test-V100
Expired
|
799 KB |
|
|
triton-unit-test-A100
Expired
|
9.32 KB |
|
|
triton-unit-test-V100
Expired
|
9.28 KB |
|
|
upstream-maxtext-10205769219-1DP1FSDP1TP1PP
Expired
|
12 KB |
|
|
upstream-maxtext-10205769219-1DP1FSDP8TP1PP
Expired
|
11.3 KB |
|
|
upstream-maxtext-10205769219-1DP2FSDP4TP1PP_single_process
Expired
|
5.92 KB |
|
|
upstream-maxtext-10205769219-1DP4FSDP2TP1PP
Expired
|
11.4 KB |
|
|
upstream-maxtext-10205769219-1DP8FSDP1TP1PP
Expired
|
11.1 KB |
|
|
upstream-maxtext-10205769219-2DP2FSDP2TP1PP
Expired
|
11.1 KB |
|
|
upstream-maxtext-10205769219-4DP2FSDP2TP1PP
Expired
|
17.4 KB |
|
|
upstream-maxtext-metrics-test-log
Expired
|
4.06 KB |
|
|
upstream-pax-10205769219-16DP1FSDP1TP1PP
Expired
|
235 KB |
|
|
upstream-pax-10205769219-1DP1FSDP1TP1PP
Expired
|
89.2 KB |
|
|
upstream-pax-10205769219-1DP2FSDP4TP1PP_single_process
Expired
|
27.1 KB |
|
|
upstream-pax-10205769219-1DP8FSDP1TP1PP
Expired
|
128 KB |
|
|
upstream-pax-10205769219-2DP1FSDP1TP4PP
Expired
|
128 KB |
|
|
upstream-pax-10205769219-2DP1FSDP2TP4PP
Expired
|
233 KB |
|
|
upstream-pax-10205769219-4DP1FSDP2TP1PP
Expired
|
127 KB |
|
|
upstream-pax-10205769219-8DP1FSDP1TP1PP
Expired
|
122 KB |
|
|
upstream-pax-10205769219-8DP1FSDP1TP1PP_eval
Expired
|
27 KB |
|
|
upstream-pax-10205769219-8DP1FSDP1TP1PP_single_process
Expired
|
27.2 KB |
|
|
upstream-pax-10205769219-LLaMA_eval
Expired
|
115 KB |
|
|
upstream-pax-metrics-test-log
Expired
|
4.31 KB |
|
|
upstream-t5x-10205769219-1P2G_fmha
Expired
|
12.4 MB |
|
|
upstream-t5x-10205769219-1P8G
Expired
|
12.4 MB |
|
|
upstream-t5x-10205769219-8G2N
Expired
|
57.1 KB |
|
|
upstream-t5x-10205769219-8G2N_fmha
Expired
|
57.2 KB |
|
|
upstream-t5x-metrics-test-log
Expired
|
6.69 KB |
|