Sample H100 job #1235
Sample H100 job #1235
Dr.CI classification results
{"FAILED":[{"workflowId":11728298718,"workflowUniqueId":89543087,"id":32671465306,"runnerName":"i-0d506f63c6bcd8768","authorEmail":"[email protected]","name":"Run Regression Tests / test (CPU Nightly, linux.4xlarge, --pre torch --index-url https://download.pytorch.org/whl/nightl... / linux-job","jobName":"test (CPU Nightly, linux.4xlarge, --pre torch --index-url https://download.pytorch.org/whl/nightl... / linux-job","conclusion":"failure","completed_at":"2024-11-07T17:48:59.000000000Z","html_url":"https://github.com/pytorch/ao/actions/runs/11728298718/job/32671465306","head_branch":"msaroufim/h100","pr_number":1235,"head_sha":"defeb5bf2b628f65f0b2bbffc1d876a534577fca","head_sha_timestamp":"2024-11-07T17:35:59.000000000Z","failure_captures":["test/prototype/test_parametrization.py::TestFakeSparsity::test_jit_trace"],"failure_lines":["FAILED test/prototype/test_parametrization.py::TestFakeSparsity::test_jit_trace - MemoryError: std::bad_alloc"],"failure_context":["+ pytest test --verbose -s","+ LD_LIBRARY_PATH=/opt/conda/lib/:/opt/rh/devtoolset-9/root/usr/lib64:/opt/rh/devtoolset-9/root/usr/lib:","+ export LD_LIBRARY_PATH=/opt/conda/lib/:/opt/rh/devtoolset-9/root/usr/lib64:/opt/rh/devtoolset-9/root/usr/lib:","+ CONDA=/opt/conda","+ export CONDA=/opt/conda","++ dirname /opt/conda/condabin","+++ dirname /opt/conda/condabin/conda","++++ which conda","+ pip install .","+ pip install -r dev-requirements.txt","+ pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/cpu","+ python -m pip install --upgrade pip"],"time":"2024-11-07T17:38:08.000000000Z"},{"workflowId":11728298718,"workflowUniqueId":89543087,"id":32671467309,"runnerName":"i-053337cce24cfbb4d","authorEmail":"[email protected]","name":"Run Regression Tests / test (CUDA 2.5, linux.g5.12xlarge.nvidia.gpu, torch==2.5.0 --index-url https://download.pytorch.o... / linux-job","jobName":"test (CUDA 2.5, linux.g5.12xlarge.nvidia.gpu, torch==2.5.0 --index-url https://download.pytorch.o... / linux-job","conclusion":"failure","completed_at":"2024-11-07T18:39:26.000000000Z","html_url":"https://github.com/pytorch/ao/actions/runs/11728298718/job/32671467309","head_branch":"msaroufim/h100","pr_number":1235,"head_sha":"defeb5bf2b628f65f0b2bbffc1d876a534577fca","head_sha_timestamp":"2024-11-07T17:35:59.000000000Z","failure_captures":["RuntimeError: Command docker exec -t afdd7ebc4de25af394eec30791420fb2402754c60be8810182a6d66790a1de8c /exec failed with exit code 1"],"failure_lines":["RuntimeError: Command docker exec -t afdd7ebc4de25af394eec30791420fb2402754c60be8810182a6d66790a1de8c /exec failed with exit code 1"],"failure_context":["+ pytest test --verbose -s","+ LD_LIBRARY_PATH=/opt/conda/lib/:/opt/rh/devtoolset-9/root/usr/lib64:/opt/rh/devtoolset-9/root/usr/lib:","+ export LD_LIBRARY_PATH=/opt/conda/lib/:/opt/rh/devtoolset-9/root/usr/lib64:/opt/rh/devtoolset-9/root/usr/lib:","+ CONDA=/opt/conda","+ export CONDA=/opt/conda","++ dirname /opt/conda/condabin","+++ dirname /opt/conda/condabin/conda","++++ which conda","+ pip install .","+ pip install -r dev-requirements.txt","+ pip install torch==2.5.0 --index-url https://download.pytorch.org/whl/cu121","+ python -m pip install --upgrade pip"],"time":"2024-11-07T17:38:10.000000000Z"},{"workflowId":11728298718,"workflowUniqueId":89543087,"id":32671467572,"runnerName":"i-0b87745dddd573f8c","authorEmail":"[email protected]","name":"Run Regression Tests / test (CUDA Nightly, linux.g5.12xlarge.nvidia.gpu, --pre torch --index-url https://download.pytorc... / linux-job","jobName":"test (CUDA Nightly, linux.g5.12xlarge.nvidia.gpu, --pre torch --index-url https://download.pytorc... / linux-job","conclusion":"failure","completed_at":"2024-11-07T18:44:52.000000000Z","html_url":"https://github.com/pytorch/ao/actions/runs/11728298718/job/32671467572","head_branch":"msaroufim/h100","pr_number":1235,"head_sha":"defeb5bf2b628f65f0b2bbffc1d876a534577fca","head_sha_timestamp":"2024-11-07T17:35:59.000000000Z","failure_captures":["test/sparsity/test_fast_sparse_training.py::TestRuntimeSemiStructuredSparsity::test_runtime_weight_sparsification_compile"],"failure_lines":["FAILED test/sparsity/test_fast_sparse_training.py::TestRuntimeSemiStructuredSparsity::test_runtime_weight_sparsification_compile - RuntimeError: CUDA error: internal error when calling cusparseLtMatmulAlgSelectionInit( &handle, &alg_sel, &matmul, CUSPARSELT_MATMUL_ALG_DEFAULT)
"],"failure_context":["+ pytest test --verbose -s","+ LD_LIBRARY_PATH=/opt/conda/lib/:/opt/rh/devtoolset-9/root/usr/lib64:/opt/rh/devtoolset-9/root/usr/lib:","+ export LD_LIBRARY_PATH=/opt/conda/lib/:/opt/rh/devtoolset-9/root/usr/lib64:/opt/rh/devtoolset-9/root/usr/lib:","+ CONDA=/opt/conda","+ export CONDA=/opt/conda","++ dirname /opt/conda/condabin","+++ dirname /opt/conda/condabin/conda","++++ which conda","+ pip install .","+ pip install -r dev-requirements.txt","+ pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu121","+ python -m pip install --upgrade pip"],"time":"2024-11-07T17:38:11.000000000Z"}],"FLAKY":[],"BROKEN_TRUNK":[],"UNSTABLE":[]}