setup.py 7.79 KB
Newer Older
lvhan028's avatar
lvhan028 committed
1
import os
2
3
import re
import sys
lvhan028's avatar
lvhan028 committed
4
5
6

from setuptools import find_packages, setup

xiabo's avatar
xiabo committed
7
8
9
10
11
import subprocess
from typing import Optional, Union
from pathlib import Path
import torch

lvhan028's avatar
lvhan028 committed
12
pwd = os.path.dirname(__file__)
lvhan028's avatar
lvhan028 committed
13
version_file = 'lmdeploy/version.py'
lvhan028's avatar
lvhan028 committed
14
15
16
17
18
19
20
21


def readme():
    with open(os.path.join(pwd, 'README.md'), encoding='utf-8') as f:
        content = f.read()
    return content


xiabo's avatar
xiabo committed
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
def get_sha(pytorch_root: Union[str, Path]) -> str:
    try:
        return subprocess.check_output(['git', 'rev-parse', 'HEAD'], cwd=pytorch_root).decode('ascii').strip()
    except Exception:
        return 'Unknown'


def get_abi():
    try:
        command = "echo '#include <string>' | gcc -x c++ -E -dM - | fgrep _GLIBCXX_USE_CXX11_ABI" 
        result = subprocess.run(command, shell=True, capture_output=True, text=True) 
        output = result.stdout.strip() 
        abi = "abi" + output.split(" ")[-1]
        return abi
    except Exception:
        return 'abiUnknown'


def get_version_add(sha: Optional[str] = None) -> str:
    version=''
    lmdeploy_root = os.path.dirname(os.path.abspath(__file__))
    add_version_path = os.path.join(os.path.join(lmdeploy_root, "lmdeploy"), "version.py")
    if sha != 'Unknown':
        if sha is None:
            sha = get_sha(lmdeploy_root)
        version = 'git' + sha[:7]

    # abi
    version += "." + get_abi()

    # dtk version
    if os.getenv("ROCM_PATH"):
        rocm_path = os.getenv('ROCM_PATH', "")
        rocm_version_path = os.path.join(rocm_path, '.info', "rocm_version")
        with open(rocm_version_path, 'r',encoding='utf-8') as file:
            lines = file.readlines()
        rocm_version=lines[0][:-2].replace(".", "")
        version += ".dtk" + rocm_version
    
    # torch version
    version += ".torch" + torch.__version__[:4]

    lines=[]
    with open(add_version_path, 'r',encoding='utf-8') as file:
        lines = file.readlines()
zhouxiang's avatar
zhouxiang committed
67
    lines[2] = "__dcu_version__ = '0.2.6+{}'\n".format(version)
xiabo's avatar
xiabo committed
68
69
70
71
    with open(add_version_path, encoding="utf-8",mode="w") as file:
        file.writelines(lines)
    file.close()

gaoqiong's avatar
gaoqiong committed
72
73
74
75
76
77
78
79
80
81
82
def copy_ck_so():
    lmdeploy_root = os.path.dirname(os.path.abspath(__file__))
    so_path = os.path.join(os.path.join(lmdeploy_root, "3rdparty"), "libgemm_multiB_int4.so")
    # dtk version
    if os.getenv("ROCM_PATH"):
        rocm_path = os.getenv('ROCM_PATH', "")    
        rocm_so_path = os.path.join(rocm_path, 'lib')
        print("rocm_so_path:",rocm_so_path)
        shutil.copy(so_path, rocm_so_path)
    else:
        shutil.copy(so_path, "usr/local/lib")
xiabo's avatar
xiabo committed
83

lvhan028's avatar
lvhan028 committed
84
def get_version():
gaoqiong's avatar
gaoqiong committed
85
    copy_ck_so()
xiabo's avatar
xiabo committed
86
87
88
    get_version_add()
    version_file = 'lmdeploy/version.py'
    with open(version_file, encoding='utf-8') as f:
lvhan028's avatar
lvhan028 committed
89
        exec(compile(f.read(), version_file, 'exec'))
xiabo's avatar
xiabo committed
90
    return locals()['__dcu_version__']
lvhan028's avatar
lvhan028 committed
91
92


Chen Xin's avatar
Chen Xin committed
93
94
95
96
97
98
def check_ext_modules():
    if os.path.exists(os.path.join(pwd, 'lmdeploy', 'lib')):
        return True
    return False


zhouxiang's avatar
zhouxiang committed
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
def get_cuda_pkgs():
    arg_name = '--cuda='
    arg_value = None
    for arg in sys.argv[1:]:
        if arg.startswith(arg_name):
            arg_value = arg[len(arg_name):]
            sys.argv.remove(arg)
            break

    cuda_pkgs = []
    if arg_value == '11':
        cuda_pkgs = [
            'nvidia-nccl-cu11', 'nvidia-cuda-runtime-cu11',
            'nvidia-cublas-cu11'
        ]
    elif arg_value == '12':
        cuda_pkgs = [
            'nvidia-nccl-cu12', 'nvidia-cuda-runtime-cu12',
            'nvidia-cublas-cu12'
        ]
    return cuda_pkgs


cuda_pkgs = get_cuda_pkgs()


125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
def parse_requirements(fname='requirements.txt', with_version=True):
    """Parse the package dependencies listed in a file but strips specific
    versioning information.

    Args:
        fname (str): path to the file
        with_version (bool, default=False): if True include version specs

    Returns:
        List[str]: list of requirements items

    CommandLine:
        python -c "import setup; print(setup.parse_requirements())"
    """
    require_fpath = fname

    def parse_line(line):
        """Parse information from a line in a requirements text file."""
        if line.startswith('-r '):
            # Allow specifying requirements in other files
            target = line.split(' ')[1]
            for info in parse_require_file(target):
                yield info
        else:
            info = {'line': line}
            if line.startswith('-e '):
                info['package'] = line.split('#egg=')[1]
            elif '@git+' in line:
                info['package'] = line
            else:
                # Remove versioning from the package
                pat = '(' + '|'.join(['>=', '==', '>']) + ')'
                parts = re.split(pat, line, maxsplit=1)
                parts = [p.strip() for p in parts]

                info['package'] = parts[0]
                if len(parts) > 1:
                    op, rest = parts[1:]
                    if ';' in rest:
                        # Handle platform specific dependencies
                        # http://setuptools.readthedocs.io/en/latest/setuptools.html#declaring-platform-specific-dependencies
                        version, platform_deps = map(str.strip,
                                                     rest.split(';'))
                        info['platform_deps'] = platform_deps
                    else:
                        version = rest  # NOQA
                    info['version'] = (op, version)
            yield info

    def parse_require_file(fpath):
        with open(fpath, 'r') as f:
            for line in f.readlines():
                line = line.strip()
                if line and not line.startswith('#'):
                    for info in parse_line(line):
                        yield info

    def gen_packages_items():
        if os.path.exists(require_fpath):
            for info in parse_require_file(require_fpath):
                parts = [info['package']]
                if with_version and 'version' in info:
                    parts.extend(info['version'])
                if not sys.version.startswith('3.4'):
                    # apparently package_deps are broken in 3.4
                    platform_deps = info.get('platform_deps')
                    if platform_deps is not None:
                        parts.append(';' + platform_deps)
                item = ''.join(parts)
                yield item

    packages = list(gen_packages_items())
zhouxiang's avatar
zhouxiang committed
197
    packages += cuda_pkgs
198
199
200
    return packages


lvhan028's avatar
lvhan028 committed
201
if __name__ == '__main__':
202
    lmdeploy_package_data = ['lmdeploy/bin/llama_gemm']
203
204
205
206
207
208
209
210
211
212
213
214
215
    setup(
        name='lmdeploy',
        version=get_version(),
        description='A toolset for compressing, deploying and serving LLM',
        long_description=readme(),
        long_description_content_type='text/markdown',
        author='OpenMMLab',
        author_email='openmmlab@gmail.com',
        packages=find_packages(exclude=()),
        package_data={
            'lmdeploy': lmdeploy_package_data,
        },
        include_package_data=True,
216
217
218
219
220
221
222
223
        setup_requires=parse_requirements('requirements/build.txt'),
        tests_require=parse_requirements('requirements/test.txt'),
        install_requires=parse_requirements('requirements/runtime.txt'),
        extras_require={
            'all': parse_requirements('requirements.txt'),
            'lite': parse_requirements('requirements/lite.txt'),
            'serve': parse_requirements('requirements/serve.txt')
        },
224
225
226
227
228
229
230
231
232
233
234
235
        has_ext_modules=check_ext_modules,
        classifiers=[
            'Programming Language :: Python :: 3.8',
            'Programming Language :: Python :: 3.9',
            'Programming Language :: Python :: 3.10',
            'Programming Language :: Python :: 3.11',
            'Intended Audience :: Developers',
            'Intended Audience :: Education',
            'Intended Audience :: Science/Research',
        ],
        entry_points={'console_scripts': ['lmdeploy = lmdeploy.cli:run']},
    )