Skip to content

Building Sage Attention | RTX 5090 | Ubuntu 25.04 | CUDA 12.8 | Python 3.12 | Triton 3.3.0 | PyTorch 2.7.0+CU128 | #244

Description

@monstari

I tried for a day but couldn't get it to work, please if someone could help.

(comfy-env-3.12) rtl-6@rtl-6-BATTLE-AX-B650M-PLUS:~/Python-3.12.0/SageAttention$ python setup.py install
Detect GPUs with compute capabilities: {'12.0'}
running install
/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/cmd.py:90: SetuptoolsDeprecationWarning: setup.py install is deprecated.
!!

        ********************************************************************************
        Please avoid running ``setup.py`` directly.
        Instead, use pypa/build, pypa/installer or other
        standards-based tools.

        By 2025-Oct-31, you need to update your project and remove deprecated calls
        or your builds will no longer be supported.

        See https://blog.ganssle.io/articles/2021/10/setup-py-deprecated.html for details.
        ********************************************************************************

!!
  self.initialize_options()
running build
running build_py
copying sageattention/core.py -> build/lib.linux-x86_64-cpython-312/sageattention
copying sageattention/__init__.py -> build/lib.linux-x86_64-cpython-312/sageattention
copying sageattention/quant.py -> build/lib.linux-x86_64-cpython-312/sageattention
copying sageattention/fa3_wrapper.py -> build/lib.linux-x86_64-cpython-312/sageattention
copying sageattention/triton/quant_per_thread.py -> build/lib.linux-x86_64-cpython-312/sageattention/triton
copying sageattention/triton/attn_qk_int8_per_block_causal.py -> build/lib.linux-x86_64-cpython-312/sageattention/triton
copying sageattention/triton/quant_per_block.py -> build/lib.linux-x86_64-cpython-312/sageattention/triton
copying sageattention/triton/attn_qk_int8_per_block_causal_varlen.py -> build/lib.linux-x86_64-cpython-312/sageattention/triton
copying sageattention/triton/attn_qk_int8_block_varlen.py -> build/lib.linux-x86_64-cpython-312/sageattention/triton
copying sageattention/triton/quant_per_block_varlen.py -> build/lib.linux-x86_64-cpython-312/sageattention/triton
copying sageattention/triton/__init__.py -> build/lib.linux-x86_64-cpython-312/sageattention/triton
copying sageattention/triton/attn_qk_int8_per_block.py -> build/lib.linux-x86_64-cpython-312/sageattention/triton
running build_ext
/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/utils/cpp_extension.py:490: UserWarning: There are no g++ version bounds defined for CUDA version 12.8
  warnings.warn(f'There are no {compiler_name} version bounds defined for CUDA version {cuda_str_version}')
building 'sageattention._qattn_sm80' extension
building 'sageattention._qattn_sm89' extension
building 'sageattention._fused' extension
Emitting ninja build file /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/build.ninja...
Emitting ninja build file /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm80/build.ninja...
Compiling objects...
Using envvar MAX_JOBS (32) as the number of workers...
Compiling objects...
Using envvar MAX_JOBS (32) as the number of workers...
Emitting ninja build file /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._fused/build.ninja...
Compiling objects...
Using envvar MAX_JOBS (32) as the number of workers...
[1/8] /usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_attn_inst_buf.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_attn_inst_buf.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_attn_inst_buf.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
FAILED: [code=255] /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_attn_inst_buf.o 
/usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_attn_inst_buf.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_attn_inst_buf.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_attn_inst_buf.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f8_cuda_sm89.cuh:17,
                 from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_attn_inst_buf.cu:2:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f8_cuda_sm89.cuh:17,
                 from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_attn_inst_buf.cu:2:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
/usr/include/x86_64-linux-gnu/bits/mathcalls.h(81): error: exception specification is incompatible with that of previous function "sinpi" (declared at line 2556 of /usr/local/cuda-12.8/include/crt/math_functions.h)
   extern double sinpi (double __x) noexcept (true); extern double __sinpi (double __x) noexcept (true);
                                    ^

1 error detected in the compilation of "/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_attn_inst_buf.cu".
[2/8] /usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
FAILED: [code=255] /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn.o 
/usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f8_cuda_sm89.cuh:17,
                 from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn.cu:2:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f8_cuda_sm89.cuh:17,
                 from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn.cu:2:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
/usr/include/x86_64-linux-gnu/bits/mathcalls.h(81): error: exception specification is incompatible with that of previous function "sinpi" (declared at line 2556 of /usr/local/cuda-12.8/include/crt/math_functions.h)
   extern double sinpi (double __x) noexcept (true); extern double __sinpi (double __x) noexcept (true);
                                    ^

1 error detected in the compilation of "/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn.cu".
[1/2] /usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm80/csrc/qattn/qk_int_sv_f16_cuda_sm80.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f16_cuda_sm80.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm80/csrc/qattn/qk_int_sv_f16_cuda_sm80.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm80 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
FAILED: [code=255] /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm80/csrc/qattn/qk_int_sv_f16_cuda_sm80.o 
/usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm80/csrc/qattn/qk_int_sv_f16_cuda_sm80.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f16_cuda_sm80.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm80/csrc/qattn/qk_int_sv_f16_cuda_sm80.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm80 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f16_cuda_sm80.cu:17:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f16_cuda_sm80.cu:17:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
/usr/include/x86_64-linux-gnu/bits/mathcalls.h(81): error: exception specification is incompatible with that of previous function "sinpi" (declared at line 2556 of /usr/local/cuda-12.8/include/crt/math_functions.h)
   extern double sinpi (double __x) noexcept (true); extern double __sinpi (double __x) noexcept (true);
                                    ^

1 error detected in the compilation of "/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f16_cuda_sm80.cu".
[1/2] /usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._fused/csrc/fused/fused.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/fused/fused.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._fused/csrc/fused/fused.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_fused -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
FAILED: [code=255] /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._fused/csrc/fused/fused.o 
/usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._fused/csrc/fused/fused.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/fused/fused.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._fused/csrc/fused/fused.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_fused -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/fused/fused.cu:21:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/fused/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/fused/fused.cu:21:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/fused/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
/usr/include/x86_64-linux-gnu/bits/mathcalls.h(81): error: exception specification is incompatible with that of previous function "sinpi" (declared at line 2556 of /usr/local/cuda-12.8/include/crt/math_functions.h)
   extern double sinpi (double __x) noexcept (true); extern double __sinpi (double __x) noexcept (true);
                                    ^

1 error detected in the compilation of "/home/rtl-6/Python-3.12.0/SageAttention/csrc/fused/fused.cu".
[3/8] /usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn_inst_buf.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn_inst_buf.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn_inst_buf.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
FAILED: [code=255] /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn_inst_buf.o 
/usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn_inst_buf.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn_inst_buf.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn_inst_buf.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f8_cuda_sm89.cuh:17,
                 from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn_inst_buf.cu:2:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f8_cuda_sm89.cuh:17,
                 from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn_inst_buf.cu:2:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
/usr/include/x86_64-linux-gnu/bits/mathcalls.h(81): error: exception specification is incompatible with that of previous function "sinpi" (declared at line 2556 of /usr/local/cuda-12.8/include/crt/math_functions.h)
   extern double sinpi (double __x) noexcept (true); extern double __sinpi (double __x) noexcept (true);
                                    ^

1 error detected in the compilation of "/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_attn_inst_buf.cu".
[4/8] /usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_fuse_v_mean_attn.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_fuse_v_mean_attn.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_fuse_v_mean_attn.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
FAILED: [code=255] /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_fuse_v_mean_attn.o 
/usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_fuse_v_mean_attn.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_fuse_v_mean_attn.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_fuse_v_mean_attn.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f8_cuda_sm89.cuh:17,
                 from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_fuse_v_mean_attn.cu:2:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f8_cuda_sm89.cuh:17,
                 from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_fuse_v_mean_attn.cu:2:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
/usr/include/x86_64-linux-gnu/bits/mathcalls.h(81): error: exception specification is incompatible with that of previous function "sinpi" (declared at line 2556 of /usr/local/cuda-12.8/include/crt/math_functions.h)
   extern double sinpi (double __x) noexcept (true); extern double __sinpi (double __x) noexcept (true);
                                    ^

1 error detected in the compilation of "/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_fuse_v_scale_fuse_v_mean_attn.cu".
[5/8] /usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
FAILED: [code=255] /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn.o 
/usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f8_cuda_sm89.cuh:17,
                 from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn.cu:2:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f8_cuda_sm89.cuh:17,
                 from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn.cu:2:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
/usr/include/x86_64-linux-gnu/bits/mathcalls.h(81): error: exception specification is incompatible with that of previous function "sinpi" (declared at line 2556 of /usr/local/cuda-12.8/include/crt/math_functions.h)
   extern double sinpi (double __x) noexcept (true); extern double __sinpi (double __x) noexcept (true);
                                    ^

1 error detected in the compilation of "/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn.cu".
[6/8] /usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn_inst_buf.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn_inst_buf.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn_inst_buf.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
FAILED: [code=255] /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn_inst_buf.o 
/usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn_inst_buf.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn_inst_buf.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn_inst_buf.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f8_cuda_sm89.cuh:17,
                 from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn_inst_buf.cu:2:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f8_cuda_sm89.cuh:17,
                 from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn_inst_buf.cu:2:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
/usr/include/x86_64-linux-gnu/bits/mathcalls.h(81): error: exception specification is incompatible with that of previous function "sinpi" (declared at line 2556 of /usr/local/cuda-12.8/include/crt/math_functions.h)
   extern double sinpi (double __x) noexcept (true); extern double __sinpi (double __x) noexcept (true);
                                    ^

1 error detected in the compilation of "/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f32_attn_inst_buf.cu".
[7/8] /usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_fuse_v_scale_attn_inst_buf.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_fuse_v_scale_attn_inst_buf.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_fuse_v_scale_attn_inst_buf.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
FAILED: [code=255] /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_fuse_v_scale_attn_inst_buf.o 
/usr/local/cuda-12.8/bin/nvcc --generate-dependencies-with-compile --dependency-output /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_fuse_v_scale_attn_inst_buf.o.d -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_fuse_v_scale_attn_inst_buf.cu -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_fuse_v_scale_attn_inst_buf.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --use_fast_math --threads=8 -Xptxas=-v -diag-suppress=174 -D_GLIBCXX_USE_CXX11_ABI=1 -gencode arch=compute_120,code=sm_120 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1 -ccbin gcc
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f8_cuda_sm89.cuh:17,
                 from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_fuse_v_scale_attn_inst_buf.cu:2:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
In file included from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/qk_int_sv_f8_cuda_sm89.cuh:17,
                 from /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_fuse_v_scale_attn_inst_buf.cu:2:
/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/../utils.cuh:36:37: warning: backslash-newline at end of file
   36 | #define CHECK_LASTDIM_CONTIGUOUS(x) \
      |                                      
/usr/include/x86_64-linux-gnu/bits/mathcalls.h(81): error: exception specification is incompatible with that of previous function "sinpi" (declared at line 2556 of /usr/local/cuda-12.8/include/crt/math_functions.h)
   extern double sinpi (double __x) noexcept (true); extern double __sinpi (double __x) noexcept (true);
                                    ^

1 error detected in the compilation of "/home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/sm89_qk_int8_sv_f8_accum_f16_fuse_v_scale_attn_inst_buf.cu".
[2/2] g++ -MMD -MF /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._fused/csrc/fused/pybind.o.d -fno-strict-overflow -Wsign-compare -DNDEBUG -g -O3 -Wall -fPIC -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/fused/pybind.cpp -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._fused/csrc/fused/pybind.o -g -O3 -fopenmp -lgomp -std=c++17 -DENABLE_BF16 -D_GLIBCXX_USE_CXX11_ABI=1 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_fused -D_GLIBCXX_USE_CXX11_ABI=1
ninja: build stopped: subcommand failed.
[8/8] g++ -MMD -MF /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/pybind_sm89.o.d -fno-strict-overflow -Wsign-compare -DNDEBUG -g -O3 -Wall -fPIC -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/pybind_sm89.cpp -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm89/csrc/qattn/pybind_sm89.o -g -O3 -fopenmp -lgomp -std=c++17 -DENABLE_BF16 -D_GLIBCXX_USE_CXX11_ABI=1 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm89 -D_GLIBCXX_USE_CXX11_ABI=1
ninja: build stopped: subcommand failed.
[2/2] g++ -MMD -MF /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm80/csrc/qattn/pybind_sm80.o.d -fno-strict-overflow -Wsign-compare -DNDEBUG -g -O3 -Wall -fPIC -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda-12.8/include -I/home/rtl-6/Python-3.12.0/comfy-env-3.12/include -I/usr/local/include/python3.12 -c -c /home/rtl-6/Python-3.12.0/SageAttention/csrc/qattn/pybind_sm80.cpp -o /home/rtl-6/Python-3.12.0/SageAttention/build/temp.linux-x86_64-cpython-312/sageattention._qattn_sm80/csrc/qattn/pybind_sm80.o -g -O3 -fopenmp -lgomp -std=c++17 -DENABLE_BF16 -D_GLIBCXX_USE_CXX11_ABI=1 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=_qattn_sm80 -D_GLIBCXX_USE_CXX11_ABI=1
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/utils/cpp_extension.py", line 2506, in _run_ninja_build
    subprocess.run(
  File "/usr/local/lib/python3.12/subprocess.py", line 571, in run
    raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ninja', '-v', '-j', '32']' returned non-zero exit status 255.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/home/rtl-6/Python-3.12.0/SageAttention/setup.py", line 220, in <module>
    setup(
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/__init__.py", line 115, in setup
    return distutils.core.setup(**attrs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/core.py", line 186, in setup
    return run_commands(dist)
           ^^^^^^^^^^^^^^^^^^
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/core.py", line 202, in run_commands
    dist.run_commands()
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/dist.py", line 1002, in run_commands
    self.run_command(cmd)
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/dist.py", line 1102, in run_command
    super().run_command(command)
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/dist.py", line 1021, in run_command
    cmd_obj.run()
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/command/install.py", line 689, in run
    self.run_command('build')
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/cmd.py", line 357, in run_command
    self.distribution.run_command(command)
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/dist.py", line 1102, in run_command
    super().run_command(command)
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/dist.py", line 1021, in run_command
    cmd_obj.run()
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/command/build.py", line 135, in run
    self.run_command(cmd_name)
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/cmd.py", line 357, in run_command
    self.distribution.run_command(command)
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/dist.py", line 1102, in run_command
    super().run_command(command)
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/dist.py", line 1021, in run_command
    cmd_obj.run()
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/command/build_ext.py", line 96, in run
    _build_ext.run(self)
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/command/build_ext.py", line 368, in run
    self.build_extensions()
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/utils/cpp_extension.py", line 1010, in build_extensions
    build_ext.build_extensions(self)
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/command/build_ext.py", line 482, in build_extensions
    self._build_extensions_parallel()
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/command/build_ext.py", line 505, in _build_extensions_parallel
    fut.result()
  File "/usr/local/lib/python3.12/concurrent/futures/_base.py", line 456, in result
    return self.__get_result()
           ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result
    raise self._exception
  File "/usr/local/lib/python3.12/concurrent/futures/thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/rtl-6/Python-3.12.0/SageAttention/setup.py", line 216, in build_extension
    objects = super().build_extension(ext)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/command/build_ext.py", line 261, in build_extension
    _build_ext.build_extension(self, ext)
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/setuptools/_distutils/command/build_ext.py", line 565, in build_extension
    objects = self.compiler.compile(
              ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/rtl-6/Python-3.12.0/SageAttention/setup.py", line 207, in compile_new
    return compile_orig(*args, **{
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/utils/cpp_extension.py", line 815, in unix_wrap_ninja_compile
    _write_ninja_file_and_compile_objects(
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/utils/cpp_extension.py", line 2159, in _write_ninja_file_and_compile_objects
    _run_ninja_build(
  File "/home/rtl-6/Python-3.12.0/comfy-env-3.12/lib/python3.12/site-packages/torch/utils/cpp_extension.py", line 2522, in _run_ninja_build
    raise RuntimeError(message) from e
RuntimeError: Error compiling objects for extension

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions