nsys-jax: re-work to be more pip-install-able #3562
ci.yaml
on: pull_request
metadata
3s
Matrix: amd64 / test-distribution
Matrix: arm64 / test-distribution
Matrix: amd64 / test-jax / run-unit-test
Matrix: amd64 / test-nsys-jax / run-unit-test
amd64
/
...
/
launch-slurm-runner
3h 25m
amd64
/
...
/
launch-slurm-runner
3h 7m
Matrix: arm64 / test-jax / run-unit-test
Waiting for pending jobs
Matrix: arm64 / test-nsys-jax / 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
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
Waiting for pending jobs
finalize
/
publish-badge
Annotations
40 errors
arm64 / build-maxtext / build-maxtext
buildx failed with: ERROR: failed to solve: process "/bin/sh -c pip-finalize.sh" did not complete successfully: exit code: 1
|
arm64 / build-upstream-t5x / build-upstream-t5x
buildx failed with: ERROR: failed to solve: process "/bin/sh -c pip-finalize.sh" did not complete successfully: exit code: 1
|
arm64 / build-upstream-pax / build-upstream-pax
buildx failed with: ERROR: failed to solve: process "/bin/sh -c pip-finalize.sh" did not complete successfully: exit code: 1
|
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-upstream-t5x / t5x-multi-node (8G2N, 8, 2)
The job running on runner jumpbox-vc69x-pktbb 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-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-upstream-t5x / t5x-multi-node (8G2N_fmha, 8, 2, --enable-fmha 1)
The job running on runner jumpbox-vc69x-lm9px 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-maxtext / maxtext-multinode (1, 4, 2, 2)
The job running on runner jumpbox-vc69x-wct7p has exceeded the maximum execution time of 360 minutes.
|
amd64 / test-maxtext / maxtext-multinode (1, 4, 2, 2)
The operation was canceled.
|
amd64 / test-rosetta-t5x / single-process-multi-device (1P1G_te-0, 1, --enable-te 0)
The job running on runner jumpbox-vc69x-qrztw has exceeded the maximum execution time of 360 minutes.
|
amd64 / test-rosetta-t5x / single-process-multi-device (1P1G_te-0, 1, --enable-te 0)
The operation was canceled.
|
amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node (1, 1)
The job running on runner jumpbox-vc69x-cgfm4 has exceeded the maximum execution time of 360 minutes.
|
amd64 / test-rosetta-t5x / vit-multi-gpu-multi-node (1, 1)
The operation was canceled.
|
amd64 / test-rosetta-t5x / vit-single-process-multi-device (8)
The job running on runner jumpbox-vc69x-s46wd has exceeded the maximum execution time of 360 minutes.
|
amd64 / test-rosetta-t5x / vit-single-process-multi-device (8)
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-bf9ml has exceeded the maximum execution time of 360 minutes.
|
|
amd64 / test-upstream-pax / pax-multi-node (16DP1FSDP1TP1PP, 1, 16, 1, 1, 4)
The job running on runner jumpbox-vc69x-vjwz9 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-t5x / multi-gpu-multi-node (2N2G_te-0, 2, 2, --enable-te 0)
The job running on runner jumpbox-vc69x-9lwpw 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 (1, 2)
The job running on runner jumpbox-vc69x-zd29f 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-upstream-pax / pax-multi-node (2DP1FSDP2TP4PP, 4, 2, 1, 2, 4)
The job running on runner jumpbox-vc69x-78pt2 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-rosetta-t5x / vit-multi-gpu-multi-node (8, 2)
The job running on runner jumpbox-vc69x-dzzd8 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-pax / rosetta-pax-multi-node-te (16DP1FSDP1TP1PP_TE, 1, 16, 1, 1, 4)
The job running on runner jumpbox-vc69x-96gsn 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-rosetta-pax / rosetta-pax-multi-node (4, 2, 1, 2)
The job running on runner jumpbox-vc69x-wf92m 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-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-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.
|
amd64 / test-nsys-jax / nsys-jax-A100-unit-test
Canceling since a higher priority waiting request for 'CI-olupton/pip-install-nsys-jax' exists
|