mirror of
https://github.com/ml-explore/mlx-examples.git
synced 2025-06-24 01:17:28 +08:00
fca087be49
* fix rotating kv cache for chat use case * reorg + fixes to caching, unify prompt caching across types and use cases for e.g. caching during a chat * nit in chat * fix tests * fix tests * fix tests * docs * chat command * comments + docs * Define meta_state on all Cache implementations * fixes + trim_prompt_cache api * fix default model --------- Co-authored-by: Angelos Katharopoulos <a_katharopoulos@apple.com>
46 lines
1.4 KiB
Python
46 lines
1.4 KiB
Python
# Copyright © 2024 Apple Inc.
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
from setuptools import setup
|
|
|
|
package_dir = Path(__file__).parent / "mlx_lm"
|
|
with open(package_dir / "requirements.txt") as fid:
|
|
requirements = [l.strip() for l in fid.readlines()]
|
|
|
|
sys.path.append(str(package_dir))
|
|
from _version import __version__
|
|
|
|
setup(
|
|
name="mlx-lm",
|
|
version=__version__,
|
|
description="LLMs on Apple silicon with MLX and the Hugging Face Hub",
|
|
long_description=open("README.md", encoding="utf-8").read(),
|
|
long_description_content_type="text/markdown",
|
|
readme="README.md",
|
|
author_email="mlx@group.apple.com",
|
|
author="MLX Contributors",
|
|
url="https://github.com/ml-explore/mlx-examples",
|
|
license="MIT",
|
|
install_requires=requirements,
|
|
packages=["mlx_lm", "mlx_lm.models", "mlx_lm.tuner"],
|
|
python_requires=">=3.8",
|
|
extras_require={
|
|
"testing": ["datasets"],
|
|
},
|
|
entry_points={
|
|
"console_scripts": [
|
|
"mlx_lm.cache_prompt = mlx_lm.cache_prompt:main",
|
|
"mlx_lm.chat = mlx_lm.chat:main",
|
|
"mlx_lm.convert = mlx_lm.convert:main",
|
|
"mlx_lm.fuse = mlx_lm.fuse:main",
|
|
"mlx_lm.generate = mlx_lm.generate:main",
|
|
"mlx_lm.lora = mlx_lm.lora:main",
|
|
"mlx_lm.merge = mlx_lm.merge:main",
|
|
"mlx_lm.server = mlx_lm.server:main",
|
|
"mlx_lm.manage = mlx_lm.manage:main",
|
|
]
|
|
},
|
|
)
|