Building wheel for flash_attn (setup.py) ... error error: subprocess-exited-with-error × pythonsetup.pybdist_wheel did not run successfully. │ exit code: 1 ╰─> [19 lines of output] fatal: Not a git repository (or any of the parent directories): .git torch.__version__ = 1.13....
Using cached flash_attn-2.2.3.post2.tar.gz (2.3 MB) Preparing metadata (setup.py) ... error error: subprocess-exited-with-error × python setup.py egg_info did not run successfully.│ exit code: 1 ╰─> [22 lines of output] fatal: not a git repository (or any of the parent dire...
fatal: not a git repository (or any of the parent directories): .git Traceback (most recent call last): File "<string>", line 2, in <module> File "<pip-setuptools-caller>", line 34, in <module> File "/tmp/pip-install-9u5e9dng/flash-attn_e362cbbd46404df8a4978593d8bb899c/setup...
fatal: not a git repository (or any of the parent directories): .git torch.__version__ = 2.1.2+cu121 running bdist_wheel Guessing wheel URL: https://github.com/Dao-AILab/flash-attention/releases/download/v2.4.2/flash_attn-2.4.2+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.w...
pytest -q -s tests/test_flash_attn.py When you encounter issues This alpha release of FlashAttention contains code written for a research project to validate ideas on speeding up attention. We have tested it on several models (BERT, GPT2, ViT). However, there might still be bugs in the...
提示:由于 Git 不支持空文件夾,创建文件夹后会生成空的 .keep 文件 assets Speedup graph for A100, d128 3年前 benchmarks Implement cross attention 3年前 csrc/flash_attn Set device for multi-GPU case 2年前 flash_attn Update README, disable backward in tests ...
!nvcc --version是否生成高于11.4的版本？根据flash-attn（https://pypi.org/project/flash-attn/）...
!nvcc --version是否生成高于11.4的版本？根据flash-attn（https://pypi.org/project/flash-attn/）...
Collecting flash-attn Using cached flash_attn-2.3.3.tar.gz (2.3 MB) Preparing metadata (setup.py) ... error error: subprocess-exited-with-error × python setup.py egg_info did not run successfully. │ exit code: 1 ╰─> [22 lines of output] fatal: not a git repository (or any of...
etc.If not causal and not local, the query @q will be rotated by rotary_cos and rotary_sin atindices cache_seqlens only (i.e. we consider all tokens in @q to be at position cache_seqlens).See tests/test_flash_attn.py::test_flash_attn_kvcache for examples of how to use this ...