ninja_required_version = 1.3
cxx = c++
nvcc = /usr/local/cuda/bin/nvcc

cflags = -DTORCH_EXTENSION_NAME=fused_mix_prec_layer_norm_cuda -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1013\" -isystem /opt/conda/lib/python3.8/site-packages/torch/include -isystem /opt/conda/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem /opt/conda/lib/python3.8/site-packages/torch/include/TH -isystem /opt/conda/lib/python3.8/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /opt/conda/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=1 -fPIC -std=c++14 -O3
post_cflags = 
cuda_cflags = -DTORCH_EXTENSION_NAME=fused_mix_prec_layer_norm_cuda -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1013\" -isystem /opt/conda/lib/python3.8/site-packages/torch/include -isystem /opt/conda/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem /opt/conda/lib/python3.8/site-packages/torch/include/TH -isystem /opt/conda/lib/python3.8/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /opt/conda/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_80,code=sm_80 --compiler-options '-fPIC' -O3 -gencode arch=compute_70,code=sm_70 --use_fast_math -maxrregcount=50 -gencode arch=compute_80,code=sm_80 -std=c++14
cuda_post_cflags = 
ldflags = -shared -L/opt/conda/lib/python3.8/site-packages/torch/lib -lc10 -lc10_cuda -ltorch_cpu -ltorch_cuda -ltorch -ltorch_python -L/usr/local/cuda/lib64 -lcudart

rule compile
  command = $cxx -MMD -MF $out.d $cflags -c $in -o $out $post_cflags
  depfile = $out.d
  deps = gcc

rule cuda_compile
  command = $nvcc $cuda_cflags -c $in -o $out $cuda_post_cflags

rule link
  command = $cxx $in $ldflags -o $out

build layer_norm_cuda.o: compile /root/ouyangxuan/project/big_model_finetune/Megatrion-LM-clear/megatron/fused_kernels/layer_norm_cuda.cpp
build layer_norm_cuda_kernel.cuda.o: cuda_compile /root/ouyangxuan/project/big_model_finetune/Megatrion-LM-clear/megatron/fused_kernels/layer_norm_cuda_kernel.cu

build fused_mix_prec_layer_norm_cuda.so: link layer_norm_cuda.o layer_norm_cuda_kernel.cuda.o

default fused_mix_prec_layer_norm_cuda.so