Dao-AILab / flash-attention

Fast and memory-efficient exact attention
BSD 3-Clause "New" or "Revised" License
13.69k stars 1.26k forks source link

build fail #843

Open uRENu opened 7 months ago

uRENu commented 7 months ago

my env:

截屏2024-02-21 18 20 43

my step: 1、python -m pip install ninja 2、git clone -b v2.4.2 https://github.com/Dao-AILab/flash-attention 3、pip install pytorch==2.1.0 torchvision torchaudio pytorch-cuda=12.1 4、sudo apt-get install python-dev libsasl2-dev gcc 5、cd flash-attention 6、git submodule update --init 7、python setup.py install

but i meet this err: torch.version = 2.1.0+cu121

running install /home/jeeves/anaconda3/envs/test/lib/python3.8/site-packages/setuptools/_distutils/cmd.py:66: SetuptoolsDeprecationWarning: setup.py install is deprecated. !!

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

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

!! self.initialize_options() /home/jeeves/anaconda3/envs/test/lib/python3.8/site-packages/setuptools/_distutils/cmd.py:66: EasyInstallDeprecationWarning: easy_install command is deprecated. !!

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

    See https://github.com/pypa/setuptools/issues/917 for details.
    ********************************************************************************

!! self.initialize_options() running bdist_egg running egg_info writing flash_attn.egg-info/PKG-INFO writing dependency_links to flash_attn.egg-info/dependency_links.txt writing requirements to flash_attn.egg-info/requires.txt writing top-level names to flash_attn.egg-info/top_level.txt reading manifest file 'flash_attn.egg-info/SOURCES.txt' reading manifest template 'MANIFEST.in' warning: no files found matching '.cu' under directory 'flash_attn' warning: no files found matching '.h' under directory 'flash_attn' warning: no files found matching '.cuh' under directory 'flash_attn' warning: no files found matching '.cpp' under directory 'flash_attn' warning: no files found matching '*.hpp' under directory 'flash_attn' adding license file 'LICENSE' adding license file 'AUTHORS' writing manifest file 'flash_attn.egg-info/SOURCES.txt' installing library code to build/bdist.linux-x86_64/egg running install_lib running build_py running build_ext /home/jeeves/anaconda3/envs/test/lib/python3.8/site-packages/torch/utils/cpp_extension.py:424: UserWarning: There are no g++ version bounds defined for CUDA version 12.1 warnings.warn(f'There are no {compiler_name} version bounds defined for CUDA version {cuda_str_version}') building 'flash_attn_2_cuda' extension Emitting ninja build file /data/flash-attention/build/temp.linux-x86_64-cpython-38/build.ninja... Compiling objects... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) 1.11.1.git.kitware.jobserver-1 g++ -pthread -B /home/jeeves/anaconda3/envs/test/compiler_compat -Wl,--sysroot=/ -pthread -shared -B /home/jeeves/anaconda3/envs/test/compiler_compat -L/home/jeeves/anaconda3/envs/test/lib -Wl,-rpath=/home/jeeves/anaconda3/envs/test/lib -Wl,--no-as-needed -Wl,--sysroot=/ /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/flash_api.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim128_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim128_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim160_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim160_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim192_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim192_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim224_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim224_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim256_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim256_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim32_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim32_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim64_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim64_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim96_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim96_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim128_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim128_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim160_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim160_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim192_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim192_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim224_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim224_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim256_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim256_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim32_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim32_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim64_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim64_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim96_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim96_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim128_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim128_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim160_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim160_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim192_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim192_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim224_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim224_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim256_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim256_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim32_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim32_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim64_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim64_fp16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim96_bf16_sm80.o /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim96_fp16_sm80.o -L/home/jeeves/anaconda3/envs/test/lib/python3.8/site-packages/torch/lib -L/usr/local/cuda/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-cpython-38/flash_attn_2_cuda.cpython-38-x86_64-linux-gnu.so g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim128_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim32_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim64_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim64_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim96_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_bwd_hdim96_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim128_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim128_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim160_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim160_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim192_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim192_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim224_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim224_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim256_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim256_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim32_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim32_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim64_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim64_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim96_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_hdim96_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim128_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim128_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim160_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim160_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim192_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim192_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim224_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim224_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim256_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim256_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim32_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim32_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim64_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim64_fp16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim96_bf16_sm80.o: No such file or directory g++: error: /data/flash-attention/build/temp.linux-x86_64-cpython-38/csrc/flash_attn/src/flash_fwd_split_hdim96_fp16_sm80.o: No such file or directory error: command '/usr/bin/g++' failed with exit code 1

leezy18 commented 6 months ago

Is your problem solved? I'm having the same problem

SaMMyCHoo commented 2 months ago

same issue, hoping for a solution.