To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.
× python setup.py egg_info did not run successfully.
│ exit code: 1
╰─> [8 lines of output]
Traceback (most recent call last):
File "", line 2, in
File "", line 34, in
File "/xxx/cache/tmp_dir/pip-install-6fkcqpqc/minference_6a95e304095b41bca85993d66c42b88e/setup.py", line 13, in
from torch.utils.cpp_extension import CUDA_HOME, BuildExtension, CUDAExtension
File "/xxx/miniconda3/envs/minference/lib/python3.10/site-packages/torch/utils/cpp_extension.py", line 28, in
from pkg_resources import packaging # type: ignore[attr-defined]
ImportError: cannot import name 'packaging' from 'pkg_resources' (/xxx/miniconda3/envs/minference/lib/python3.10/site-packages/pkg_resources/init.py)
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
error: metadata-generation-failed
× Encountered error while generating package metadata.
╰─> See above for output.
note: This is an issue with the package mentioned above, not pip.
hint: See above for details.
Describe the bug
pip install minference Looking in indexes: https://mirrors.cloud.tencent.com/pypi/simple Collecting minference Using cached https://mirrors.cloud.tencent.com/pypi/packages/26/0a/d4e339371c8b3673bd353ba51fdb55f381905f31daf2fb715d030d1d0c18/minference-0.1.3.tar.gz (57 kB) Preparing metadata (setup.py) ... error error: subprocess-exited-with-error
× python setup.py egg_info did not run successfully. │ exit code: 1 ╰─> [8 lines of output] Traceback (most recent call last): File "", line 2, in
File "", line 34, in
File "/xxx/cache/tmp_dir/pip-install-6fkcqpqc/minference_6a95e304095b41bca85993d66c42b88e/setup.py", line 13, in
from torch.utils.cpp_extension import CUDA_HOME, BuildExtension, CUDAExtension
File "/xxx/miniconda3/envs/minference/lib/python3.10/site-packages/torch/utils/cpp_extension.py", line 28, in
from pkg_resources import packaging # type: ignore[attr-defined]
ImportError: cannot import name 'packaging' from 'pkg_resources' (/xxx/miniconda3/envs/minference/lib/python3.10/site-packages/pkg_resources/init.py)
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip. error: metadata-generation-failed
× Encountered error while generating package metadata. ╰─> See above for output.
note: This is an issue with the package mentioned above, not pip. hint: See above for details.
Steps to reproduce
No response
Expected Behavior
No response
Logs
No response
Additional Information
No response