Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

remove the dependency on AutoGPTQ for CPU and bump to V0.4.3 #380

Merged
merged 6 commits into from
Dec 16, 2024
Merged
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
bump version to 0.4.3 and update installation instructions
Signed-off-by: Sun, Xuehao <[email protected]>
XuehaoSun committed Dec 11, 2024
commit c430017de3c2f0f90750d607b2e1b07074de0c33
20 changes: 2 additions & 18 deletions README.md
Original file line number Diff line number Diff line change
@@ -5,7 +5,7 @@ AutoRound
<h3> Advanced Quantization Algorithm for LLMs</h3>

[![python](https://img.shields.io/badge/python-3.9%2B-blue)](https://github.com/intel/auto-round)
[![version](https://img.shields.io/badge/release-0.4.2-green)](https://github.com/intel/auto-round)
[![version](https://img.shields.io/badge/release-0.4.3-green)](https://github.com/intel/auto-round)
[![license](https://img.shields.io/badge/license-Apache%202-blue)](https://github.com/intel/auto-round/blob/main/LICENSE)
---
<div align="left">
@@ -48,30 +48,14 @@ more accuracy data and recipes across various models.
### Install from pypi

```bash
# GPU
pip install auto-round

# CPU
pip install auto-round[cpu]

# HPU
pip install auto-round[hpu]
```

<details>
<summary>Build from Source</summary>

```bash
pip install -r requirements.txt

# GPU
pip install -vvv --no-build-isolation -e .

# CPU
pip install -vvv --no-build-isolation -e .[cpu]

# HPU
pip install -vvv --no-build-isolation -e .[hpu]
pip install -vvv --no-build-isolation .
```

</details>
2 changes: 1 addition & 1 deletion auto_round/version.py
Original file line number Diff line number Diff line change
@@ -14,4 +14,4 @@
"""Intel® auto-round: An open-source Python library
supporting popular model weight only compression based on signround."""

__version__ = "0.4.2"
__version__ = "0.4.3"
1 change: 0 additions & 1 deletion requirements-cpu.txt
Original file line number Diff line number Diff line change
@@ -9,7 +9,6 @@ threadpoolctl
lm-eval>=0.4.2,<0.5
tqdm
packaging
auto-gptq>=0.7.1
pillow
numba
tbb
18 changes: 13 additions & 5 deletions setup.py
Original file line number Diff line number Diff line change
@@ -111,6 +111,19 @@ def detect_local_sm_architectures():
return arch_list


def detect_hardware():
try:
os.system("pip install torch")
except:
print("Failed to install torch")
if is_hpu_available():
return "requirements-hpu.txt"
elif is_cuda_available():
return "requirements.txt"
else:
return "requirements-cpu.txt"


UNSUPPORTED_COMPUTE_CAPABILITIES = ['3.5', '3.7', '5.0', '5.2', '5.3']

if BUILD_CUDA_EXT:
@@ -220,10 +233,6 @@ def detect_local_sm_architectures():
],
),
"install_requires": fetch_requirements("requirements.txt"),
"extras_require": {
"hpu": fetch_requirements("requirements-hpu.txt"),
"cpu": fetch_requirements("requirements-cpu.txt"),
},
}

if __name__ == "__main__":
@@ -248,7 +257,6 @@ def detect_local_sm_architectures():
url="https://github.com/intel/auto-round",
packages=include_packages,
include_dirs=include_dirs,
##include_package_data=False,
install_requires=install_requires,
extras_require=extras_require,
python_requires=">=3.7.0",