Compiling cuda extensions with HIP version: 4.3.22313-cccb3896 clang version 14.0.0 (http://10.8.150.239/dcutoolkit/driverruntime/llvm-project.git 458573e609dd35aac1fa72e6136853de2b7651c8) Target: x86_64-unknown-linux-gnu Thread model: posix InstalledDir: /opt/dtk-22.04.2/llvm/bin from /opt/dtk-22.04.2/bin torch.__version__ = 1.10.0a0+gitc7f69d6-dtk22042 nvcc was not found. CUDA extension will not be installed. If you're installing within a container from https://hub.docker.com/r/pytorch/pytorch, only images whose names contain 'devel' will provide nvcc. /public/home/huchen/colossalAI/ColossalAI/MANIFEST.in -> /public/home/huchen/colossalAI/ColossalAI/MANIFEST.in ok /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/scaled_upper_triang_masked_softmax.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/compat.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/compat.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/type_shim.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/type_shim.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/scaled_upper_triang_masked_softmax_cuda.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax_hip.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/multi_tensor_apply.cuh -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_apply.cuh skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/multi_tensor_sgd_kernel.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_sgd_kernel.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/multi_tensor_scale_kernel.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_scale_kernel.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/multi_tensor_adam.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_adam.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/scaled_masked_softmax.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/scaled_masked_softmax_cuda.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax_hip.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/layer_norm_cuda.cpp -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/layer_norm_hip.cpp skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/scaled_upper_triang_masked_softmax.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/scaled_masked_softmax.cpp -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.cpp skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/colossal_C_frontend.cpp -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/colossal_C_frontend.cpp skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/multi_tensor_lamb.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_lamb.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/type_shim.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/type_shim.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/layer_norm_cuda_kernel.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/layer_norm_hip_kernel.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/multihead_attention_1d.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/multi_tensor_l2norm_kernel.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_l2norm_kernel.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/compat.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/compat.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/multihead_attention_1d.cpp -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.cpp skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/scaled_upper_triang_masked_softmax.cpp -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.cpp skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/multi_tensor_apply.cuh -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_apply.cuh skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/cross_entropy.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/cross_entropy.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/normalize_kernels.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/normalize_kernels.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/cuda_util.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/hip_util.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/dropout_kernels.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/dropout_kernels.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/cublas_wrappers.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/cublas_wrappers.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/transform_kernels.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/transform_kernels.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/softmax_kernels.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/softmax_kernels.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/general_kernels.cu -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/general_kernels.hip skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/cublas_wrappers.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cublas_wrappers.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/strided_batch_gemm.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/strided_batch_gemm.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/kernels.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/kernels.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/feed_forward.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/feed_forward.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/cublas_wrappers.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cublas_wrappers.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/dropout.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/dropout.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/normalize_layer.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/normalize_layer.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/block_reduce.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/block_reduce.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/cuda_util.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/hip_util.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/context.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/context.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/ls_cub.cuh -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/ls_cub.cuh skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/cross_entropy_layer.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cross_entropy_layer.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/softmax.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/softmax.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/cuda_util.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/hip_util.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/cuda_native/csrc/kernels/include/kernels.h -> /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/kernels.h skipped /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/colossal_C_frontend.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/type_shim.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/compat.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_apply.cuh -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/layer_norm_hip.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/strided_batch_gemm.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/feed_forward.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cublas_wrappers.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/dropout.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/normalize_layer.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/block_reduce.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/context.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/ls_cub.cuh -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cross_entropy_layer.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/hip_util.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/kernels.h -> None ignored Total number of unsupported CUDA function calls: 0 Total number of replaced kernel launches: 139 /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/colossal_C_frontend.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/type_shim.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/compat.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_apply.cuh -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/layer_norm_hip.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/strided_batch_gemm.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/feed_forward.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cublas_wrappers.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/dropout.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/normalize_layer.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/block_reduce.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/context.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/ls_cub.cuh -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cross_entropy_layer.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/hip_util.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/kernels.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_sgd_kernel.hip -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_scale_kernel.hip -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_adam.hip -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_l2norm_kernel.hip -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_lamb.hip -> None ignored Total number of unsupported CUDA function calls: 0 Total number of replaced kernel launches: 0 /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/colossal_C_frontend.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/type_shim.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/compat.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_apply.cuh -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/layer_norm_hip.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/strided_batch_gemm.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/feed_forward.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cublas_wrappers.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/dropout.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/normalize_layer.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/block_reduce.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/context.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/ls_cub.cuh -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cross_entropy_layer.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/hip_util.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/kernels.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax_hip.hip -> None ignored Total number of unsupported CUDA function calls: 0 Total number of replaced kernel launches: 0 /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/colossal_C_frontend.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/type_shim.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/compat.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_apply.cuh -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/layer_norm_hip.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/strided_batch_gemm.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/feed_forward.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cublas_wrappers.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/dropout.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/normalize_layer.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/block_reduce.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/context.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/ls_cub.cuh -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cross_entropy_layer.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/hip_util.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/kernels.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax_hip.hip -> None ignored Total number of unsupported CUDA function calls: 0 Total number of replaced kernel launches: 0 /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/colossal_C_frontend.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/type_shim.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/compat.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_apply.cuh -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/layer_norm_hip.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/strided_batch_gemm.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/feed_forward.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cublas_wrappers.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/dropout.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/normalize_layer.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/block_reduce.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/context.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/ls_cub.cuh -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cross_entropy_layer.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/hip_util.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/kernels.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/layer_norm_hip_kernel.hip -> None ignored Total number of unsupported CUDA function calls: 0 Total number of replaced kernel launches: 0 /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/colossal_C_frontend.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/type_shim.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/compat.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_apply.cuh -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/layer_norm_hip.cpp -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/strided_batch_gemm.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/feed_forward.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cublas_wrappers.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/dropout.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/normalize_layer.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/block_reduce.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/context.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/ls_cub.cuh -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/cross_entropy_layer.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/hip_util.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/softmax.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/include/kernels.h -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/cublas_wrappers.hip -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/transform_kernels.hip -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/dropout_kernels.hip -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/normalize_kernels.hip -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/softmax_kernels.hip -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/general_kernels.hip -> None ignored /public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/hip_util.hip -> None ignored Total number of unsupported CUDA function calls: 0 Total number of replaced kernel launches: 0 running bdist_wheel running build running build_py not copying model_zoo/helper.py (output up-to-date) not copying model_zoo/__init__.py (output up-to-date) not copying colossalai/global_variables.py (output up-to-date) not copying colossalai/initialize.py (output up-to-date) not copying colossalai/constants.py (output up-to-date) not copying colossalai/__init__.py (output up-to-date) not copying colossalai/core.py (output up-to-date) not copying model_zoo/bert/__init__.py (output up-to-date) not copying model_zoo/gpt/gpt.py (output up-to-date) not copying model_zoo/gpt/__init__.py (output up-to-date) not copying model_zoo/mlp_mixer/__init__.py (output up-to-date) not copying model_zoo/moe/models.py (output up-to-date) not copying model_zoo/moe/util.py (output up-to-date) not copying model_zoo/moe/__init__.py (output up-to-date) not copying model_zoo/vit/vit.py (output up-to-date) not copying model_zoo/vit/vision_transformer_from_config.py (output up-to-date) not copying model_zoo/vit/__init__.py (output up-to-date) not copying model_zoo/mlp_mixer/parallel_3d/__init__.py (output up-to-date) not copying model_zoo/mlp_mixer/parallel_3d/mlp_mixer.py (output up-to-date) not copying colossalai/logging/logging.py (output up-to-date) not copying colossalai/logging/__init__.py (output up-to-date) not copying colossalai/amp/__init__.py (output up-to-date) not copying colossalai/amp/amp_type.py (output up-to-date) not copying colossalai/zero/zero_redundancy_optimizer_level_3.py (output up-to-date) not copying colossalai/zero/zero_redundancy_optimizer_level_2.py (output up-to-date) not copying colossalai/zero/__init__.py (output up-to-date) not copying colossalai/zero/loss_scaler.py (output up-to-date) not copying colossalai/engine/__init__.py (output up-to-date) not copying colossalai/engine/_base_engine.py (output up-to-date) not copying colossalai/trainer/_trainer.py (output up-to-date) not copying colossalai/trainer/__init__.py (output up-to-date) not copying colossalai/registry/__init__.py (output up-to-date) not copying colossalai/registry/registry.py (output up-to-date) not copying colossalai/utils/checkpointing.py (output up-to-date) not copying colossalai/utils/activation_checkpoint.py (output up-to-date) not copying colossalai/utils/timer.py (output up-to-date) not copying colossalai/utils/common.py (output up-to-date) not copying colossalai/utils/memory.py (output up-to-date) not copying colossalai/utils/__init__.py (output up-to-date) not copying colossalai/utils/cuda.py (output up-to-date) not copying colossalai/nn/init.py (output up-to-date) not copying colossalai/nn/__init__.py (output up-to-date) not copying colossalai/builder/builder.py (output up-to-date) not copying colossalai/builder/__init__.py (output up-to-date) not copying colossalai/builder/pipeline.py (output up-to-date) not copying colossalai/context/config.py (output up-to-date) not copying colossalai/context/parallel_context.py (output up-to-date) not copying colossalai/context/parallel_mode.py (output up-to-date) not copying colossalai/context/__init__.py (output up-to-date) not copying colossalai/communication/p2p.py (output up-to-date) not copying colossalai/communication/utils.py (output up-to-date) not copying colossalai/communication/collective.py (output up-to-date) not copying colossalai/communication/__init__.py (output up-to-date) not copying colossalai/communication/ring.py (output up-to-date) not copying colossalai/kernel/__init__.py (output up-to-date) not copying colossalai/amp/apex_amp/apex_amp.py (output up-to-date) not copying colossalai/amp/apex_amp/__init__.py (output up-to-date) not copying colossalai/amp/naive_amp/__init__.py (output up-to-date) not copying colossalai/amp/naive_amp/_fp16_optimizer.py (output up-to-date) not copying colossalai/amp/naive_amp/naive_amp.py (output up-to-date) not copying colossalai/amp/torch_amp/torch_amp.py (output up-to-date) not copying colossalai/amp/torch_amp/_grad_scaler.py (output up-to-date) not copying colossalai/amp/torch_amp/__init__.py (output up-to-date) not copying colossalai/engine/ophooks/_memtracer_ophook.py (output up-to-date) not copying colossalai/engine/ophooks/_base_ophook.py (output up-to-date) not copying colossalai/engine/ophooks/__init__.py (output up-to-date) not copying colossalai/engine/schedule/_base_schedule.py (output up-to-date) not copying colossalai/engine/schedule/_pipeline_schedule.py (output up-to-date) not copying colossalai/engine/schedule/_non_pipeline_schedule.py (output up-to-date) not copying colossalai/engine/schedule/__init__.py (output up-to-date) not copying colossalai/engine/gradient_handler/_pipeline_parallel_gradient_handler.py (output up-to-date) not copying colossalai/engine/gradient_handler/_data_parallel_gradient_handler.py (output up-to-date) not copying colossalai/engine/gradient_handler/_base_gradient_handler.py (output up-to-date) not copying colossalai/engine/gradient_handler/_moe_gradient_handler.py (output up-to-date) not copying colossalai/engine/gradient_handler/_zero_gradient_handler.py (output up-to-date) not copying colossalai/engine/gradient_handler/_sequence_parallel_gradient_handler.py (output up-to-date) not copying colossalai/engine/gradient_handler/__init__.py (output up-to-date) not copying colossalai/trainer/hooks/_log_hook.py (output up-to-date) not copying colossalai/trainer/hooks/_checkpoint_hook.py (output up-to-date) not copying colossalai/trainer/hooks/__init__.py (output up-to-date) not copying colossalai/trainer/hooks/_base_hook.py (output up-to-date) not copying colossalai/trainer/hooks/_metric_hook.py (output up-to-date) not copying colossalai/trainer/hooks/_lr_scheduler_hook.py (output up-to-date) not copying colossalai/utils/data_sampler/data_parallel_sampler.py (output up-to-date) not copying colossalai/utils/data_sampler/base_sampler.py (output up-to-date) not copying colossalai/utils/data_sampler/__init__.py (output up-to-date) not copying colossalai/utils/multi_tensor_apply/multi_tensor_apply.py (output up-to-date) not copying colossalai/utils/multi_tensor_apply/__init__.py (output up-to-date) not copying colossalai/utils/gradient_accumulation/__init__.py (output up-to-date) not copying colossalai/utils/gradient_accumulation/_gradient_accumulation.py (output up-to-date) not copying colossalai/nn/optimizer/fused_adam.py (output up-to-date) not copying colossalai/nn/optimizer/lars.py (output up-to-date) not copying colossalai/nn/optimizer/fused_sgd.py (output up-to-date) not copying colossalai/nn/optimizer/fused_lamb.py (output up-to-date) not copying colossalai/nn/optimizer/__init__.py (output up-to-date) not copying colossalai/nn/optimizer/lamb.py (output up-to-date) not copying colossalai/nn/optimizer/colossalai_optimizer.py (output up-to-date) not copying colossalai/nn/layer/base_layer.py (output up-to-date) not copying colossalai/nn/layer/__init__.py (output up-to-date) not copying colossalai/nn/model/model_from_config.py (output up-to-date) not copying colossalai/nn/model/__init__.py (output up-to-date) not copying colossalai/nn/metric/_utils.py (output up-to-date) not copying colossalai/nn/metric/accuracy_3d.py (output up-to-date) not copying colossalai/nn/metric/accuracy_2p5d.py (output up-to-date) not copying colossalai/nn/metric/accuracy_2d.py (output up-to-date) not copying colossalai/nn/metric/__init__.py (output up-to-date) not copying colossalai/nn/lr_scheduler/delayed.py (output up-to-date) not copying colossalai/nn/lr_scheduler/torch.py (output up-to-date) not copying colossalai/nn/lr_scheduler/cosine.py (output up-to-date) not copying colossalai/nn/lr_scheduler/multistep.py (output up-to-date) not copying colossalai/nn/lr_scheduler/onecycle.py (output up-to-date) not copying colossalai/nn/lr_scheduler/linear.py (output up-to-date) not copying colossalai/nn/lr_scheduler/__init__.py (output up-to-date) not copying colossalai/nn/lr_scheduler/poly.py (output up-to-date) not copying colossalai/nn/loss/loss_3d.py (output up-to-date) not copying colossalai/nn/loss/loss_2d.py (output up-to-date) not copying colossalai/nn/loss/__init__.py (output up-to-date) not copying colossalai/nn/loss/loss_2p5d.py (output up-to-date) not copying colossalai/nn/loss/loss_moe.py (output up-to-date) not copying colossalai/nn/loss/loss_1d.py (output up-to-date) not copying colossalai/nn/layer/parallel_2d/_utils.py (output up-to-date) not copying colossalai/nn/layer/parallel_2d/layers.py (output up-to-date) not copying colossalai/nn/layer/parallel_2d/_operation.py (output up-to-date) not copying colossalai/nn/layer/parallel_2d/__init__.py (output up-to-date) not copying colossalai/nn/layer/parallel_1d/_utils.py (output up-to-date) not copying colossalai/nn/layer/parallel_1d/layers.py (output up-to-date) not copying colossalai/nn/layer/parallel_1d/_operation.py (output up-to-date) not copying colossalai/nn/layer/parallel_1d/__init__.py (output up-to-date) not copying colossalai/nn/layer/colossalai_layer/_utils.py (output up-to-date) not copying colossalai/nn/layer/colossalai_layer/embedding.py (output up-to-date) not copying colossalai/nn/layer/colossalai_layer/linear.py (output up-to-date) not copying colossalai/nn/layer/colossalai_layer/normalization.py (output up-to-date) not copying colossalai/nn/layer/colossalai_layer/dropout.py (output up-to-date) not copying colossalai/nn/layer/colossalai_layer/__init__.py (output up-to-date) not copying colossalai/nn/layer/parallel_sequence/_utils.py (output up-to-date) not copying colossalai/nn/layer/parallel_sequence/layers.py (output up-to-date) not copying colossalai/nn/layer/parallel_sequence/_operation.py (output up-to-date) not copying colossalai/nn/layer/parallel_sequence/__init__.py (output up-to-date) not copying colossalai/nn/layer/vanilla/layers.py (output up-to-date) not copying colossalai/nn/layer/vanilla/__init__.py (output up-to-date) not copying colossalai/nn/layer/moe/layers.py (output up-to-date) not copying colossalai/nn/layer/moe/_operation.py (output up-to-date) not copying colossalai/nn/layer/moe/__init__.py (output up-to-date) not copying colossalai/nn/layer/utils/common.py (output up-to-date) not copying colossalai/nn/layer/utils/__init__.py (output up-to-date) not copying colossalai/nn/layer/parallel_3d/_utils.py (output up-to-date) not copying colossalai/nn/layer/parallel_3d/layers.py (output up-to-date) not copying colossalai/nn/layer/parallel_3d/_operation.py (output up-to-date) not copying colossalai/nn/layer/parallel_3d/__init__.py (output up-to-date) not copying colossalai/nn/layer/wrapper/lambda_wrapper.py (output up-to-date) not copying colossalai/nn/layer/wrapper/pipeline_wrapper.py (output up-to-date) not copying colossalai/nn/layer/wrapper/__init__.py (output up-to-date) not copying colossalai/nn/layer/parallel_2p5d/_utils.py (output up-to-date) not copying colossalai/nn/layer/parallel_2p5d/layers.py (output up-to-date) not copying colossalai/nn/layer/parallel_2p5d/_operation.py (output up-to-date) not copying colossalai/nn/layer/parallel_2p5d/__init__.py (output up-to-date) not copying colossalai/context/random/_helper.py (output up-to-date) not copying colossalai/context/random/seed_manager.py (output up-to-date) not copying colossalai/context/random/__init__.py (output up-to-date) not copying colossalai/context/process_group_initializer/initializer_2p5d.py (output up-to-date) not copying colossalai/context/process_group_initializer/initializer_tensor.py (output up-to-date) not copying colossalai/context/process_group_initializer/initializer_data.py (output up-to-date) not copying colossalai/context/process_group_initializer/initializer_3d.py (output up-to-date) not copying colossalai/context/process_group_initializer/initializer_sequence.py (output up-to-date) not copying colossalai/context/process_group_initializer/initializer_moe.py (output up-to-date) not copying colossalai/context/process_group_initializer/initializer_model.py (output up-to-date) not copying colossalai/context/process_group_initializer/initializer_2d.py (output up-to-date) not copying colossalai/context/process_group_initializer/__init__.py (output up-to-date) not copying colossalai/context/process_group_initializer/initializer_1d.py (output up-to-date) not copying colossalai/context/process_group_initializer/initializer_pipeline.py (output up-to-date) not copying colossalai/context/process_group_initializer/process_group_initializer.py (output up-to-date) not copying colossalai/kernel/cuda_native/scaled_softmax.py (output up-to-date) not copying colossalai/kernel/cuda_native/layer_norm.py (output up-to-date) not copying colossalai/kernel/cuda_native/__init__.py (output up-to-date) not copying colossalai/kernel/cuda_native/multihead_attention.py (output up-to-date) not copying colossalai/kernel/jit/bias_gelu.py (output up-to-date) not copying colossalai/kernel/jit/option.py (output up-to-date) not copying colossalai/kernel/jit/bias_dropout_add.py (output up-to-date) not copying colossalai/kernel/jit/__init__.py (output up-to-date) running build_ext building 'colossal_C' extension Emitting ninja build file /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/build.ninja... Compiling objects... Using envvar MAX_JOBS (32) as the number of workers... Successfully preprocessed all matching files. Successfully preprocessed all matching files. Successfully preprocessed all matching files. Successfully preprocessed all matching files. Successfully preprocessed all matching files. Successfully preprocessed all matching files. ninja: no work to do. g++ -pthread -shared /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_l2norm_kernel.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_sgd_kernel.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_scale_kernel.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/colossal_C_frontend.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_adam.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multi_tensor_lamb.o -L/usr/local/lib/python3.7/site-packages/torch/lib -L/opt/dtk-22.04.2/lib -L/usr/local/lib -lc10 -ltorch -ltorch_cpu -ltorch_python -lamdhip64 -lc10_hip -ltorch_hip -lpython3.7m -o build/lib.linux-x86_64-3.7/colossal_C.cpython-37m-x86_64-linux-gnu.so building 'colossal_scaled_upper_triang_masked_softmax' extension Emitting ninja build file /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/build.ninja... Compiling objects... Using envvar MAX_JOBS (32) as the number of workers... ninja: no work to do. g++ -pthread -shared /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_upper_triang_masked_softmax_hip.o -L/usr/local/lib/python3.7/site-packages/torch/lib -L/opt/dtk-22.04.2/lib -L/usr/local/lib -lc10 -ltorch -ltorch_cpu -ltorch_python -lamdhip64 -lc10_hip -ltorch_hip -lpython3.7m -o build/lib.linux-x86_64-3.7/colossal_scaled_upper_triang_masked_softmax.cpython-37m-x86_64-linux-gnu.so building 'colossal_scaled_masked_softmax' extension Emitting ninja build file /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/build.ninja... Compiling objects... Using envvar MAX_JOBS (32) as the number of workers... ninja: no work to do. g++ -pthread -shared /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/scaled_masked_softmax_hip.o -L/usr/local/lib/python3.7/site-packages/torch/lib -L/opt/dtk-22.04.2/lib -L/usr/local/lib -lc10 -ltorch -ltorch_cpu -ltorch_python -lamdhip64 -lc10_hip -ltorch_hip -lpython3.7m -o build/lib.linux-x86_64-3.7/colossal_scaled_masked_softmax.cpython-37m-x86_64-linux-gnu.so building 'colossal_layer_norm_cuda' extension Emitting ninja build file /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/build.ninja... Compiling objects... Using envvar MAX_JOBS (32) as the number of workers... ninja: no work to do. g++ -pthread -shared /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/layer_norm_hip.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/layer_norm_hip_kernel.o -L/usr/local/lib/python3.7/site-packages/torch/lib -L/opt/dtk-22.04.2/lib -L/usr/local/lib -lc10 -ltorch -ltorch_cpu -ltorch_python -lamdhip64 -lc10_hip -ltorch_hip -lpython3.7m -o build/lib.linux-x86_64-3.7/colossal_layer_norm_cuda.cpython-37m-x86_64-linux-gnu.so building 'colossal_multihead_attention' extension Emitting ninja build file /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/build.ninja... Compiling objects... Using envvar MAX_JOBS (32) as the number of workers... ninja: no work to do. g++ -pthread -shared /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/softmax_kernels.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/cublas_wrappers.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/multihead_attention_1d.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/normalize_kernels.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/general_kernels.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/hip_util.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/transform_kernels.o /public/home/huchen/colossalAI/ColossalAI/build/temp.linux-x86_64-3.7/public/home/huchen/colossalAI/ColossalAI/colossalai/kernel/hip_native/csrc/kernels/dropout_kernels.o -L/usr/local/lib/python3.7/site-packages/torch/lib -L/opt/dtk-22.04.2/lib -L/usr/local/lib -lc10 -ltorch -ltorch_cpu -ltorch_python -lamdhip64 -lc10_hip -ltorch_hip -lpython3.7m -o build/lib.linux-x86_64-3.7/colossal_multihead_attention.cpython-37m-x86_64-linux-gnu.so installing to build/bdist.linux-x86_64/wheel running install running install_lib creating build/bdist.linux-x86_64/wheel copying build/lib.linux-x86_64-3.7/colossal_multihead_attention.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/wheel copying build/lib.linux-x86_64-3.7/colossal_layer_norm_cuda.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/wheel copying build/lib.linux-x86_64-3.7/colossal_scaled_masked_softmax.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/wheel copying build/lib.linux-x86_64-3.7/colossal_scaled_upper_triang_masked_softmax.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/wheel copying build/lib.linux-x86_64-3.7/colossal_C.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/wheel creating build/bdist.linux-x86_64/wheel/model_zoo copying build/lib.linux-x86_64-3.7/model_zoo/helper.py -> build/bdist.linux-x86_64/wheel/model_zoo creating build/bdist.linux-x86_64/wheel/model_zoo/bert copying build/lib.linux-x86_64-3.7/model_zoo/bert/__init__.py -> build/bdist.linux-x86_64/wheel/model_zoo/bert creating build/bdist.linux-x86_64/wheel/model_zoo/gpt copying build/lib.linux-x86_64-3.7/model_zoo/gpt/gpt.py -> build/bdist.linux-x86_64/wheel/model_zoo/gpt copying build/lib.linux-x86_64-3.7/model_zoo/gpt/__init__.py -> build/bdist.linux-x86_64/wheel/model_zoo/gpt creating build/bdist.linux-x86_64/wheel/model_zoo/mlp_mixer copying build/lib.linux-x86_64-3.7/model_zoo/mlp_mixer/__init__.py -> build/bdist.linux-x86_64/wheel/model_zoo/mlp_mixer creating build/bdist.linux-x86_64/wheel/model_zoo/mlp_mixer/parallel_3d copying build/lib.linux-x86_64-3.7/model_zoo/mlp_mixer/parallel_3d/__init__.py -> build/bdist.linux-x86_64/wheel/model_zoo/mlp_mixer/parallel_3d copying build/lib.linux-x86_64-3.7/model_zoo/mlp_mixer/parallel_3d/mlp_mixer.py -> build/bdist.linux-x86_64/wheel/model_zoo/mlp_mixer/parallel_3d creating build/bdist.linux-x86_64/wheel/model_zoo/moe copying build/lib.linux-x86_64-3.7/model_zoo/moe/models.py -> build/bdist.linux-x86_64/wheel/model_zoo/moe copying build/lib.linux-x86_64-3.7/model_zoo/moe/util.py -> build/bdist.linux-x86_64/wheel/model_zoo/moe copying build/lib.linux-x86_64-3.7/model_zoo/moe/__init__.py -> build/bdist.linux-x86_64/wheel/model_zoo/moe copying build/lib.linux-x86_64-3.7/model_zoo/__init__.py -> build/bdist.linux-x86_64/wheel/model_zoo creating build/bdist.linux-x86_64/wheel/model_zoo/vit copying build/lib.linux-x86_64-3.7/model_zoo/vit/vit.py -> build/bdist.linux-x86_64/wheel/model_zoo/vit copying build/lib.linux-x86_64-3.7/model_zoo/vit/vision_transformer_from_config.py -> build/bdist.linux-x86_64/wheel/model_zoo/vit copying build/lib.linux-x86_64-3.7/model_zoo/vit/__init__.py -> build/bdist.linux-x86_64/wheel/model_zoo/vit creating build/bdist.linux-x86_64/wheel/colossalai creating build/bdist.linux-x86_64/wheel/colossalai/logging copying build/lib.linux-x86_64-3.7/colossalai/logging/logging.py -> build/bdist.linux-x86_64/wheel/colossalai/logging copying build/lib.linux-x86_64-3.7/colossalai/logging/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/logging creating build/bdist.linux-x86_64/wheel/colossalai/amp creating build/bdist.linux-x86_64/wheel/colossalai/amp/apex_amp copying build/lib.linux-x86_64-3.7/colossalai/amp/apex_amp/apex_amp.py -> build/bdist.linux-x86_64/wheel/colossalai/amp/apex_amp copying build/lib.linux-x86_64-3.7/colossalai/amp/apex_amp/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/amp/apex_amp creating build/bdist.linux-x86_64/wheel/colossalai/amp/naive_amp copying build/lib.linux-x86_64-3.7/colossalai/amp/naive_amp/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/amp/naive_amp copying build/lib.linux-x86_64-3.7/colossalai/amp/naive_amp/_fp16_optimizer.py -> build/bdist.linux-x86_64/wheel/colossalai/amp/naive_amp copying build/lib.linux-x86_64-3.7/colossalai/amp/naive_amp/naive_amp.py -> build/bdist.linux-x86_64/wheel/colossalai/amp/naive_amp copying build/lib.linux-x86_64-3.7/colossalai/amp/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/amp copying build/lib.linux-x86_64-3.7/colossalai/amp/amp_type.py -> build/bdist.linux-x86_64/wheel/colossalai/amp creating build/bdist.linux-x86_64/wheel/colossalai/amp/torch_amp copying build/lib.linux-x86_64-3.7/colossalai/amp/torch_amp/torch_amp.py -> build/bdist.linux-x86_64/wheel/colossalai/amp/torch_amp copying build/lib.linux-x86_64-3.7/colossalai/amp/torch_amp/_grad_scaler.py -> build/bdist.linux-x86_64/wheel/colossalai/amp/torch_amp copying build/lib.linux-x86_64-3.7/colossalai/amp/torch_amp/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/amp/torch_amp creating build/bdist.linux-x86_64/wheel/colossalai/zero copying build/lib.linux-x86_64-3.7/colossalai/zero/zero_redundancy_optimizer_level_3.py -> build/bdist.linux-x86_64/wheel/colossalai/zero copying build/lib.linux-x86_64-3.7/colossalai/zero/zero_redundancy_optimizer_level_2.py -> build/bdist.linux-x86_64/wheel/colossalai/zero copying build/lib.linux-x86_64-3.7/colossalai/zero/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/zero copying build/lib.linux-x86_64-3.7/colossalai/zero/loss_scaler.py -> build/bdist.linux-x86_64/wheel/colossalai/zero copying build/lib.linux-x86_64-3.7/colossalai/global_variables.py -> build/bdist.linux-x86_64/wheel/colossalai creating build/bdist.linux-x86_64/wheel/colossalai/engine copying build/lib.linux-x86_64-3.7/colossalai/engine/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/engine creating build/bdist.linux-x86_64/wheel/colossalai/engine/ophooks copying build/lib.linux-x86_64-3.7/colossalai/engine/ophooks/_memtracer_ophook.py -> build/bdist.linux-x86_64/wheel/colossalai/engine/ophooks copying build/lib.linux-x86_64-3.7/colossalai/engine/ophooks/_base_ophook.py -> build/bdist.linux-x86_64/wheel/colossalai/engine/ophooks copying build/lib.linux-x86_64-3.7/colossalai/engine/ophooks/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/engine/ophooks creating build/bdist.linux-x86_64/wheel/colossalai/engine/schedule copying build/lib.linux-x86_64-3.7/colossalai/engine/schedule/_base_schedule.py -> build/bdist.linux-x86_64/wheel/colossalai/engine/schedule copying build/lib.linux-x86_64-3.7/colossalai/engine/schedule/_pipeline_schedule.py -> build/bdist.linux-x86_64/wheel/colossalai/engine/schedule copying build/lib.linux-x86_64-3.7/colossalai/engine/schedule/_non_pipeline_schedule.py -> build/bdist.linux-x86_64/wheel/colossalai/engine/schedule copying build/lib.linux-x86_64-3.7/colossalai/engine/schedule/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/engine/schedule copying build/lib.linux-x86_64-3.7/colossalai/engine/_base_engine.py -> build/bdist.linux-x86_64/wheel/colossalai/engine creating build/bdist.linux-x86_64/wheel/colossalai/engine/gradient_handler copying build/lib.linux-x86_64-3.7/colossalai/engine/gradient_handler/_pipeline_parallel_gradient_handler.py -> build/bdist.linux-x86_64/wheel/colossalai/engine/gradient_handler copying build/lib.linux-x86_64-3.7/colossalai/engine/gradient_handler/_data_parallel_gradient_handler.py -> build/bdist.linux-x86_64/wheel/colossalai/engine/gradient_handler copying build/lib.linux-x86_64-3.7/colossalai/engine/gradient_handler/_base_gradient_handler.py -> build/bdist.linux-x86_64/wheel/colossalai/engine/gradient_handler copying build/lib.linux-x86_64-3.7/colossalai/engine/gradient_handler/_moe_gradient_handler.py -> build/bdist.linux-x86_64/wheel/colossalai/engine/gradient_handler copying build/lib.linux-x86_64-3.7/colossalai/engine/gradient_handler/_zero_gradient_handler.py -> build/bdist.linux-x86_64/wheel/colossalai/engine/gradient_handler copying build/lib.linux-x86_64-3.7/colossalai/engine/gradient_handler/_sequence_parallel_gradient_handler.py -> build/bdist.linux-x86_64/wheel/colossalai/engine/gradient_handler copying build/lib.linux-x86_64-3.7/colossalai/engine/gradient_handler/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/engine/gradient_handler creating build/bdist.linux-x86_64/wheel/colossalai/trainer copying build/lib.linux-x86_64-3.7/colossalai/trainer/_trainer.py -> build/bdist.linux-x86_64/wheel/colossalai/trainer creating build/bdist.linux-x86_64/wheel/colossalai/trainer/hooks copying build/lib.linux-x86_64-3.7/colossalai/trainer/hooks/_log_hook.py -> build/bdist.linux-x86_64/wheel/colossalai/trainer/hooks copying build/lib.linux-x86_64-3.7/colossalai/trainer/hooks/_checkpoint_hook.py -> build/bdist.linux-x86_64/wheel/colossalai/trainer/hooks copying build/lib.linux-x86_64-3.7/colossalai/trainer/hooks/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/trainer/hooks copying build/lib.linux-x86_64-3.7/colossalai/trainer/hooks/_base_hook.py -> build/bdist.linux-x86_64/wheel/colossalai/trainer/hooks copying build/lib.linux-x86_64-3.7/colossalai/trainer/hooks/_metric_hook.py -> build/bdist.linux-x86_64/wheel/colossalai/trainer/hooks copying build/lib.linux-x86_64-3.7/colossalai/trainer/hooks/_lr_scheduler_hook.py -> build/bdist.linux-x86_64/wheel/colossalai/trainer/hooks copying build/lib.linux-x86_64-3.7/colossalai/trainer/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/trainer creating build/bdist.linux-x86_64/wheel/colossalai/registry copying build/lib.linux-x86_64-3.7/colossalai/registry/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/registry copying build/lib.linux-x86_64-3.7/colossalai/registry/registry.py -> build/bdist.linux-x86_64/wheel/colossalai/registry copying build/lib.linux-x86_64-3.7/colossalai/initialize.py -> build/bdist.linux-x86_64/wheel/colossalai copying build/lib.linux-x86_64-3.7/colossalai/constants.py -> build/bdist.linux-x86_64/wheel/colossalai copying build/lib.linux-x86_64-3.7/colossalai/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai creating build/bdist.linux-x86_64/wheel/colossalai/utils copying build/lib.linux-x86_64-3.7/colossalai/utils/checkpointing.py -> build/bdist.linux-x86_64/wheel/colossalai/utils creating build/bdist.linux-x86_64/wheel/colossalai/utils/data_sampler copying build/lib.linux-x86_64-3.7/colossalai/utils/data_sampler/data_parallel_sampler.py -> build/bdist.linux-x86_64/wheel/colossalai/utils/data_sampler copying build/lib.linux-x86_64-3.7/colossalai/utils/data_sampler/base_sampler.py -> build/bdist.linux-x86_64/wheel/colossalai/utils/data_sampler copying build/lib.linux-x86_64-3.7/colossalai/utils/data_sampler/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/utils/data_sampler creating build/bdist.linux-x86_64/wheel/colossalai/utils/multi_tensor_apply copying build/lib.linux-x86_64-3.7/colossalai/utils/multi_tensor_apply/multi_tensor_apply.py -> build/bdist.linux-x86_64/wheel/colossalai/utils/multi_tensor_apply copying build/lib.linux-x86_64-3.7/colossalai/utils/multi_tensor_apply/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/utils/multi_tensor_apply creating build/bdist.linux-x86_64/wheel/colossalai/utils/gradient_accumulation copying build/lib.linux-x86_64-3.7/colossalai/utils/gradient_accumulation/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/utils/gradient_accumulation copying build/lib.linux-x86_64-3.7/colossalai/utils/gradient_accumulation/_gradient_accumulation.py -> build/bdist.linux-x86_64/wheel/colossalai/utils/gradient_accumulation copying build/lib.linux-x86_64-3.7/colossalai/utils/activation_checkpoint.py -> build/bdist.linux-x86_64/wheel/colossalai/utils copying build/lib.linux-x86_64-3.7/colossalai/utils/timer.py -> build/bdist.linux-x86_64/wheel/colossalai/utils copying build/lib.linux-x86_64-3.7/colossalai/utils/common.py -> build/bdist.linux-x86_64/wheel/colossalai/utils copying build/lib.linux-x86_64-3.7/colossalai/utils/memory.py -> build/bdist.linux-x86_64/wheel/colossalai/utils copying build/lib.linux-x86_64-3.7/colossalai/utils/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/utils copying build/lib.linux-x86_64-3.7/colossalai/utils/cuda.py -> build/bdist.linux-x86_64/wheel/colossalai/utils creating build/bdist.linux-x86_64/wheel/colossalai/nn creating build/bdist.linux-x86_64/wheel/colossalai/nn/optimizer copying build/lib.linux-x86_64-3.7/colossalai/nn/optimizer/fused_adam.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/optimizer copying build/lib.linux-x86_64-3.7/colossalai/nn/optimizer/lars.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/optimizer copying build/lib.linux-x86_64-3.7/colossalai/nn/optimizer/fused_sgd.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/optimizer copying build/lib.linux-x86_64-3.7/colossalai/nn/optimizer/fused_lamb.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/optimizer copying build/lib.linux-x86_64-3.7/colossalai/nn/optimizer/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/optimizer copying build/lib.linux-x86_64-3.7/colossalai/nn/optimizer/lamb.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/optimizer copying build/lib.linux-x86_64-3.7/colossalai/nn/optimizer/colossalai_optimizer.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/optimizer creating build/bdist.linux-x86_64/wheel/colossalai/nn/layer copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/base_layer.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer creating build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_2d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_2d/_utils.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_2d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_2d/layers.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_2d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_2d/_operation.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_2d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_2d/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_2d creating build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_1d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_1d/_utils.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_1d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_1d/layers.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_1d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_1d/_operation.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_1d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_1d/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_1d creating build/bdist.linux-x86_64/wheel/colossalai/nn/layer/colossalai_layer copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/colossalai_layer/_utils.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/colossalai_layer copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/colossalai_layer/embedding.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/colossalai_layer copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/colossalai_layer/linear.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/colossalai_layer copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/colossalai_layer/normalization.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/colossalai_layer copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/colossalai_layer/dropout.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/colossalai_layer copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/colossalai_layer/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/colossalai_layer creating build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_sequence copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_sequence/_utils.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_sequence copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_sequence/layers.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_sequence copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_sequence/_operation.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_sequence copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_sequence/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_sequence creating build/bdist.linux-x86_64/wheel/colossalai/nn/layer/vanilla copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/vanilla/layers.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/vanilla copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/vanilla/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/vanilla creating build/bdist.linux-x86_64/wheel/colossalai/nn/layer/moe copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/moe/layers.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/moe copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/moe/_operation.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/moe copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/moe/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/moe copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer creating build/bdist.linux-x86_64/wheel/colossalai/nn/layer/utils copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/utils/common.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/utils copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/utils/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/utils creating build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_3d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_3d/_utils.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_3d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_3d/layers.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_3d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_3d/_operation.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_3d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_3d/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_3d creating build/bdist.linux-x86_64/wheel/colossalai/nn/layer/wrapper copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/wrapper/lambda_wrapper.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/wrapper copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/wrapper/pipeline_wrapper.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/wrapper copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/wrapper/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/wrapper creating build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_2p5d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_2p5d/_utils.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_2p5d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_2p5d/layers.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_2p5d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_2p5d/_operation.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_2p5d copying build/lib.linux-x86_64-3.7/colossalai/nn/layer/parallel_2p5d/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/layer/parallel_2p5d creating build/bdist.linux-x86_64/wheel/colossalai/nn/model copying build/lib.linux-x86_64-3.7/colossalai/nn/model/model_from_config.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/model copying build/lib.linux-x86_64-3.7/colossalai/nn/model/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/model copying build/lib.linux-x86_64-3.7/colossalai/nn/init.py -> build/bdist.linux-x86_64/wheel/colossalai/nn copying build/lib.linux-x86_64-3.7/colossalai/nn/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn creating build/bdist.linux-x86_64/wheel/colossalai/nn/metric copying build/lib.linux-x86_64-3.7/colossalai/nn/metric/_utils.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/metric copying build/lib.linux-x86_64-3.7/colossalai/nn/metric/accuracy_3d.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/metric copying build/lib.linux-x86_64-3.7/colossalai/nn/metric/accuracy_2p5d.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/metric copying build/lib.linux-x86_64-3.7/colossalai/nn/metric/accuracy_2d.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/metric copying build/lib.linux-x86_64-3.7/colossalai/nn/metric/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/metric creating build/bdist.linux-x86_64/wheel/colossalai/nn/lr_scheduler copying build/lib.linux-x86_64-3.7/colossalai/nn/lr_scheduler/delayed.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/lr_scheduler copying build/lib.linux-x86_64-3.7/colossalai/nn/lr_scheduler/torch.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/lr_scheduler copying build/lib.linux-x86_64-3.7/colossalai/nn/lr_scheduler/cosine.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/lr_scheduler copying build/lib.linux-x86_64-3.7/colossalai/nn/lr_scheduler/multistep.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/lr_scheduler copying build/lib.linux-x86_64-3.7/colossalai/nn/lr_scheduler/onecycle.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/lr_scheduler copying build/lib.linux-x86_64-3.7/colossalai/nn/lr_scheduler/linear.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/lr_scheduler copying build/lib.linux-x86_64-3.7/colossalai/nn/lr_scheduler/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/lr_scheduler copying build/lib.linux-x86_64-3.7/colossalai/nn/lr_scheduler/poly.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/lr_scheduler creating build/bdist.linux-x86_64/wheel/colossalai/nn/loss copying build/lib.linux-x86_64-3.7/colossalai/nn/loss/loss_3d.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/loss copying build/lib.linux-x86_64-3.7/colossalai/nn/loss/loss_2d.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/loss copying build/lib.linux-x86_64-3.7/colossalai/nn/loss/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/loss copying build/lib.linux-x86_64-3.7/colossalai/nn/loss/loss_2p5d.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/loss copying build/lib.linux-x86_64-3.7/colossalai/nn/loss/loss_moe.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/loss copying build/lib.linux-x86_64-3.7/colossalai/nn/loss/loss_1d.py -> build/bdist.linux-x86_64/wheel/colossalai/nn/loss creating build/bdist.linux-x86_64/wheel/colossalai/builder copying build/lib.linux-x86_64-3.7/colossalai/builder/builder.py -> build/bdist.linux-x86_64/wheel/colossalai/builder copying build/lib.linux-x86_64-3.7/colossalai/builder/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/builder copying build/lib.linux-x86_64-3.7/colossalai/builder/pipeline.py -> build/bdist.linux-x86_64/wheel/colossalai/builder creating build/bdist.linux-x86_64/wheel/colossalai/context copying build/lib.linux-x86_64-3.7/colossalai/context/config.py -> build/bdist.linux-x86_64/wheel/colossalai/context copying build/lib.linux-x86_64-3.7/colossalai/context/parallel_context.py -> build/bdist.linux-x86_64/wheel/colossalai/context copying build/lib.linux-x86_64-3.7/colossalai/context/parallel_mode.py -> build/bdist.linux-x86_64/wheel/colossalai/context copying build/lib.linux-x86_64-3.7/colossalai/context/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/context creating build/bdist.linux-x86_64/wheel/colossalai/context/random copying build/lib.linux-x86_64-3.7/colossalai/context/random/_helper.py -> build/bdist.linux-x86_64/wheel/colossalai/context/random copying build/lib.linux-x86_64-3.7/colossalai/context/random/seed_manager.py -> build/bdist.linux-x86_64/wheel/colossalai/context/random copying build/lib.linux-x86_64-3.7/colossalai/context/random/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/context/random creating build/bdist.linux-x86_64/wheel/colossalai/context/process_group_initializer copying build/lib.linux-x86_64-3.7/colossalai/context/process_group_initializer/initializer_2p5d.py -> build/bdist.linux-x86_64/wheel/colossalai/context/process_group_initializer copying build/lib.linux-x86_64-3.7/colossalai/context/process_group_initializer/initializer_tensor.py -> build/bdist.linux-x86_64/wheel/colossalai/context/process_group_initializer copying build/lib.linux-x86_64-3.7/colossalai/context/process_group_initializer/initializer_data.py -> build/bdist.linux-x86_64/wheel/colossalai/context/process_group_initializer copying build/lib.linux-x86_64-3.7/colossalai/context/process_group_initializer/initializer_3d.py -> build/bdist.linux-x86_64/wheel/colossalai/context/process_group_initializer copying build/lib.linux-x86_64-3.7/colossalai/context/process_group_initializer/initializer_sequence.py -> build/bdist.linux-x86_64/wheel/colossalai/context/process_group_initializer copying build/lib.linux-x86_64-3.7/colossalai/context/process_group_initializer/initializer_moe.py -> build/bdist.linux-x86_64/wheel/colossalai/context/process_group_initializer copying build/lib.linux-x86_64-3.7/colossalai/context/process_group_initializer/initializer_model.py -> build/bdist.linux-x86_64/wheel/colossalai/context/process_group_initializer copying build/lib.linux-x86_64-3.7/colossalai/context/process_group_initializer/initializer_2d.py -> build/bdist.linux-x86_64/wheel/colossalai/context/process_group_initializer copying build/lib.linux-x86_64-3.7/colossalai/context/process_group_initializer/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/context/process_group_initializer copying build/lib.linux-x86_64-3.7/colossalai/context/process_group_initializer/initializer_1d.py -> build/bdist.linux-x86_64/wheel/colossalai/context/process_group_initializer copying build/lib.linux-x86_64-3.7/colossalai/context/process_group_initializer/initializer_pipeline.py -> build/bdist.linux-x86_64/wheel/colossalai/context/process_group_initializer copying build/lib.linux-x86_64-3.7/colossalai/context/process_group_initializer/process_group_initializer.py -> build/bdist.linux-x86_64/wheel/colossalai/context/process_group_initializer creating build/bdist.linux-x86_64/wheel/colossalai/communication copying build/lib.linux-x86_64-3.7/colossalai/communication/p2p.py -> build/bdist.linux-x86_64/wheel/colossalai/communication copying build/lib.linux-x86_64-3.7/colossalai/communication/utils.py -> build/bdist.linux-x86_64/wheel/colossalai/communication copying build/lib.linux-x86_64-3.7/colossalai/communication/collective.py -> build/bdist.linux-x86_64/wheel/colossalai/communication copying build/lib.linux-x86_64-3.7/colossalai/communication/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/communication copying build/lib.linux-x86_64-3.7/colossalai/communication/ring.py -> build/bdist.linux-x86_64/wheel/colossalai/communication copying build/lib.linux-x86_64-3.7/colossalai/core.py -> build/bdist.linux-x86_64/wheel/colossalai creating build/bdist.linux-x86_64/wheel/colossalai/kernel creating build/bdist.linux-x86_64/wheel/colossalai/kernel/cuda_native copying build/lib.linux-x86_64-3.7/colossalai/kernel/cuda_native/scaled_softmax.py -> build/bdist.linux-x86_64/wheel/colossalai/kernel/cuda_native copying build/lib.linux-x86_64-3.7/colossalai/kernel/cuda_native/layer_norm.py -> build/bdist.linux-x86_64/wheel/colossalai/kernel/cuda_native copying build/lib.linux-x86_64-3.7/colossalai/kernel/cuda_native/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/kernel/cuda_native copying build/lib.linux-x86_64-3.7/colossalai/kernel/cuda_native/multihead_attention.py -> build/bdist.linux-x86_64/wheel/colossalai/kernel/cuda_native creating build/bdist.linux-x86_64/wheel/colossalai/kernel/jit copying build/lib.linux-x86_64-3.7/colossalai/kernel/jit/bias_gelu.py -> build/bdist.linux-x86_64/wheel/colossalai/kernel/jit copying build/lib.linux-x86_64-3.7/colossalai/kernel/jit/option.py -> build/bdist.linux-x86_64/wheel/colossalai/kernel/jit copying build/lib.linux-x86_64-3.7/colossalai/kernel/jit/bias_dropout_add.py -> build/bdist.linux-x86_64/wheel/colossalai/kernel/jit copying build/lib.linux-x86_64-3.7/colossalai/kernel/jit/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/kernel/jit copying build/lib.linux-x86_64-3.7/colossalai/kernel/__init__.py -> build/bdist.linux-x86_64/wheel/colossalai/kernel running install_egg_info running egg_info writing colossalai.egg-info/PKG-INFO writing dependency_links to colossalai.egg-info/dependency_links.txt writing requirements to colossalai.egg-info/requires.txt writing top-level names to colossalai.egg-info/top_level.txt 'license_file' option was not specified reading manifest file 'colossalai.egg-info/SOURCES.txt' reading manifest template 'MANIFEST.in' warning: no files found matching '*.txt' warning: no files found matching '*.tr' under directory 'colossalai' warning: no files found matching '*.cc' under directory 'colossalai' writing manifest file 'colossalai.egg-info/SOURCES.txt' Copying colossalai.egg-info to build/bdist.linux-x86_64/wheel/colossalai-0.0.2-py3.7.egg-info Copying top_level.txt to build/bdist.linux-x86_64/wheel/colossalai-0.0.2-py3.7.egg-info/top_level.txt Copying PKG-INFO to build/bdist.linux-x86_64/wheel/colossalai-0.0.2-py3.7.egg-info/PKG-INFO Copying dependency_links.txt to build/bdist.linux-x86_64/wheel/colossalai-0.0.2-py3.7.egg-info/dependency_links.txt Copying requires.txt to build/bdist.linux-x86_64/wheel/colossalai-0.0.2-py3.7.egg-info/requires.txt Copying SOURCES.txt to build/bdist.linux-x86_64/wheel/colossalai-0.0.2-py3.7.egg-info/SOURCES.txt running install_scripts adding license file "LICENSE" (matched pattern "LICEN[CS]E*") creating build/bdist.linux-x86_64/wheel/colossalai-0.0.2.dist-info/WHEEL creating 'dist/colossalai-0.0.2-cp37-cp37m-linux_x86_64.whl' and adding 'build/bdist.linux-x86_64/wheel' to it adding 'colossal_C.cpython-37m-x86_64-linux-gnu.so' adding 'colossal_layer_norm_cuda.cpython-37m-x86_64-linux-gnu.so' adding 'colossal_multihead_attention.cpython-37m-x86_64-linux-gnu.so' adding 'colossal_scaled_masked_softmax.cpython-37m-x86_64-linux-gnu.so' adding 'colossal_scaled_upper_triang_masked_softmax.cpython-37m-x86_64-linux-gnu.so' adding 'colossalai/__init__.py' adding 'colossalai/constants.py' adding 'colossalai/core.py' adding 'colossalai/global_variables.py' adding 'colossalai/initialize.py' adding 'colossalai/amp/__init__.py' adding 'colossalai/amp/amp_type.py' adding 'colossalai/amp/apex_amp/__init__.py' adding 'colossalai/amp/apex_amp/apex_amp.py' adding 'colossalai/amp/naive_amp/__init__.py' adding 'colossalai/amp/naive_amp/_fp16_optimizer.py' adding 'colossalai/amp/naive_amp/naive_amp.py' adding 'colossalai/amp/torch_amp/__init__.py' adding 'colossalai/amp/torch_amp/_grad_scaler.py' adding 'colossalai/amp/torch_amp/torch_amp.py' adding 'colossalai/builder/__init__.py' adding 'colossalai/builder/builder.py' adding 'colossalai/builder/pipeline.py' adding 'colossalai/communication/__init__.py' adding 'colossalai/communication/collective.py' adding 'colossalai/communication/p2p.py' adding 'colossalai/communication/ring.py' adding 'colossalai/communication/utils.py' adding 'colossalai/context/__init__.py' adding 'colossalai/context/config.py' adding 'colossalai/context/parallel_context.py' adding 'colossalai/context/parallel_mode.py' adding 'colossalai/context/process_group_initializer/__init__.py' adding 'colossalai/context/process_group_initializer/initializer_1d.py' adding 'colossalai/context/process_group_initializer/initializer_2d.py' adding 'colossalai/context/process_group_initializer/initializer_2p5d.py' adding 'colossalai/context/process_group_initializer/initializer_3d.py' adding 'colossalai/context/process_group_initializer/initializer_data.py' adding 'colossalai/context/process_group_initializer/initializer_model.py' adding 'colossalai/context/process_group_initializer/initializer_moe.py' adding 'colossalai/context/process_group_initializer/initializer_pipeline.py' adding 'colossalai/context/process_group_initializer/initializer_sequence.py' adding 'colossalai/context/process_group_initializer/initializer_tensor.py' adding 'colossalai/context/process_group_initializer/process_group_initializer.py' adding 'colossalai/context/random/__init__.py' adding 'colossalai/context/random/_helper.py' adding 'colossalai/context/random/seed_manager.py' adding 'colossalai/engine/__init__.py' adding 'colossalai/engine/_base_engine.py' adding 'colossalai/engine/gradient_handler/__init__.py' adding 'colossalai/engine/gradient_handler/_base_gradient_handler.py' adding 'colossalai/engine/gradient_handler/_data_parallel_gradient_handler.py' adding 'colossalai/engine/gradient_handler/_moe_gradient_handler.py' adding 'colossalai/engine/gradient_handler/_pipeline_parallel_gradient_handler.py' adding 'colossalai/engine/gradient_handler/_sequence_parallel_gradient_handler.py' adding 'colossalai/engine/gradient_handler/_zero_gradient_handler.py' adding 'colossalai/engine/ophooks/__init__.py' adding 'colossalai/engine/ophooks/_base_ophook.py' adding 'colossalai/engine/ophooks/_memtracer_ophook.py' adding 'colossalai/engine/schedule/__init__.py' adding 'colossalai/engine/schedule/_base_schedule.py' adding 'colossalai/engine/schedule/_non_pipeline_schedule.py' adding 'colossalai/engine/schedule/_pipeline_schedule.py' adding 'colossalai/kernel/__init__.py' adding 'colossalai/kernel/cuda_native/__init__.py' adding 'colossalai/kernel/cuda_native/layer_norm.py' adding 'colossalai/kernel/cuda_native/multihead_attention.py' adding 'colossalai/kernel/cuda_native/scaled_softmax.py' adding 'colossalai/kernel/jit/__init__.py' adding 'colossalai/kernel/jit/bias_dropout_add.py' adding 'colossalai/kernel/jit/bias_gelu.py' adding 'colossalai/kernel/jit/option.py' adding 'colossalai/logging/__init__.py' adding 'colossalai/logging/logging.py' adding 'colossalai/nn/__init__.py' adding 'colossalai/nn/init.py' adding 'colossalai/nn/layer/__init__.py' adding 'colossalai/nn/layer/base_layer.py' adding 'colossalai/nn/layer/colossalai_layer/__init__.py' adding 'colossalai/nn/layer/colossalai_layer/_utils.py' adding 'colossalai/nn/layer/colossalai_layer/dropout.py' adding 'colossalai/nn/layer/colossalai_layer/embedding.py' adding 'colossalai/nn/layer/colossalai_layer/linear.py' adding 'colossalai/nn/layer/colossalai_layer/normalization.py' adding 'colossalai/nn/layer/moe/__init__.py' adding 'colossalai/nn/layer/moe/_operation.py' adding 'colossalai/nn/layer/moe/layers.py' adding 'colossalai/nn/layer/parallel_1d/__init__.py' adding 'colossalai/nn/layer/parallel_1d/_operation.py' adding 'colossalai/nn/layer/parallel_1d/_utils.py' adding 'colossalai/nn/layer/parallel_1d/layers.py' adding 'colossalai/nn/layer/parallel_2d/__init__.py' adding 'colossalai/nn/layer/parallel_2d/_operation.py' adding 'colossalai/nn/layer/parallel_2d/_utils.py' adding 'colossalai/nn/layer/parallel_2d/layers.py' adding 'colossalai/nn/layer/parallel_2p5d/__init__.py' adding 'colossalai/nn/layer/parallel_2p5d/_operation.py' adding 'colossalai/nn/layer/parallel_2p5d/_utils.py' adding 'colossalai/nn/layer/parallel_2p5d/layers.py' adding 'colossalai/nn/layer/parallel_3d/__init__.py' adding 'colossalai/nn/layer/parallel_3d/_operation.py' adding 'colossalai/nn/layer/parallel_3d/_utils.py' adding 'colossalai/nn/layer/parallel_3d/layers.py' adding 'colossalai/nn/layer/parallel_sequence/__init__.py' adding 'colossalai/nn/layer/parallel_sequence/_operation.py' adding 'colossalai/nn/layer/parallel_sequence/_utils.py' adding 'colossalai/nn/layer/parallel_sequence/layers.py' adding 'colossalai/nn/layer/utils/__init__.py' adding 'colossalai/nn/layer/utils/common.py' adding 'colossalai/nn/layer/vanilla/__init__.py' adding 'colossalai/nn/layer/vanilla/layers.py' adding 'colossalai/nn/layer/wrapper/__init__.py' adding 'colossalai/nn/layer/wrapper/lambda_wrapper.py' adding 'colossalai/nn/layer/wrapper/pipeline_wrapper.py' adding 'colossalai/nn/loss/__init__.py' adding 'colossalai/nn/loss/loss_1d.py' adding 'colossalai/nn/loss/loss_2d.py' adding 'colossalai/nn/loss/loss_2p5d.py' adding 'colossalai/nn/loss/loss_3d.py' adding 'colossalai/nn/loss/loss_moe.py' adding 'colossalai/nn/lr_scheduler/__init__.py' adding 'colossalai/nn/lr_scheduler/cosine.py' adding 'colossalai/nn/lr_scheduler/delayed.py' adding 'colossalai/nn/lr_scheduler/linear.py' adding 'colossalai/nn/lr_scheduler/multistep.py' adding 'colossalai/nn/lr_scheduler/onecycle.py' adding 'colossalai/nn/lr_scheduler/poly.py' adding 'colossalai/nn/lr_scheduler/torch.py' adding 'colossalai/nn/metric/__init__.py' adding 'colossalai/nn/metric/_utils.py' adding 'colossalai/nn/metric/accuracy_2d.py' adding 'colossalai/nn/metric/accuracy_2p5d.py' adding 'colossalai/nn/metric/accuracy_3d.py' adding 'colossalai/nn/model/__init__.py' adding 'colossalai/nn/model/model_from_config.py' adding 'colossalai/nn/optimizer/__init__.py' adding 'colossalai/nn/optimizer/colossalai_optimizer.py' adding 'colossalai/nn/optimizer/fused_adam.py' adding 'colossalai/nn/optimizer/fused_lamb.py' adding 'colossalai/nn/optimizer/fused_sgd.py' adding 'colossalai/nn/optimizer/lamb.py' adding 'colossalai/nn/optimizer/lars.py' adding 'colossalai/registry/__init__.py' adding 'colossalai/registry/registry.py' adding 'colossalai/trainer/__init__.py' adding 'colossalai/trainer/_trainer.py' adding 'colossalai/trainer/hooks/__init__.py' adding 'colossalai/trainer/hooks/_base_hook.py' adding 'colossalai/trainer/hooks/_checkpoint_hook.py' adding 'colossalai/trainer/hooks/_log_hook.py' adding 'colossalai/trainer/hooks/_lr_scheduler_hook.py' adding 'colossalai/trainer/hooks/_metric_hook.py' adding 'colossalai/utils/__init__.py' adding 'colossalai/utils/activation_checkpoint.py' adding 'colossalai/utils/checkpointing.py' adding 'colossalai/utils/common.py' adding 'colossalai/utils/cuda.py' adding 'colossalai/utils/memory.py' adding 'colossalai/utils/timer.py' adding 'colossalai/utils/data_sampler/__init__.py' adding 'colossalai/utils/data_sampler/base_sampler.py' adding 'colossalai/utils/data_sampler/data_parallel_sampler.py' adding 'colossalai/utils/gradient_accumulation/__init__.py' adding 'colossalai/utils/gradient_accumulation/_gradient_accumulation.py' adding 'colossalai/utils/multi_tensor_apply/__init__.py' adding 'colossalai/utils/multi_tensor_apply/multi_tensor_apply.py' adding 'colossalai/zero/__init__.py' adding 'colossalai/zero/loss_scaler.py' adding 'colossalai/zero/zero_redundancy_optimizer_level_2.py' adding 'colossalai/zero/zero_redundancy_optimizer_level_3.py' adding 'model_zoo/__init__.py' adding 'model_zoo/helper.py' adding 'model_zoo/bert/__init__.py' adding 'model_zoo/gpt/__init__.py' adding 'model_zoo/gpt/gpt.py' adding 'model_zoo/mlp_mixer/__init__.py' adding 'model_zoo/mlp_mixer/parallel_3d/__init__.py' adding 'model_zoo/mlp_mixer/parallel_3d/mlp_mixer.py' adding 'model_zoo/moe/__init__.py' adding 'model_zoo/moe/models.py' adding 'model_zoo/moe/util.py' adding 'model_zoo/vit/__init__.py' adding 'model_zoo/vit/vision_transformer_from_config.py' adding 'model_zoo/vit/vit.py' adding 'colossalai-0.0.2.dist-info/LICENSE' adding 'colossalai-0.0.2.dist-info/METADATA' adding 'colossalai-0.0.2.dist-info/WHEEL' adding 'colossalai-0.0.2.dist-info/top_level.txt' adding 'colossalai-0.0.2.dist-info/RECORD' removing build/bdist.linux-x86_64/wheel