bench_other.py 8.06 KB
Newer Older
Liangsheng Yin's avatar
Liangsheng Yin committed
1
2
3
4
5
6
7
8
9
10
11
import argparse
import json
import time
from concurrent.futures import ThreadPoolExecutor
from functools import partial

import guidance
from sglang.test.test_utils import (
    add_common_other_args_and_parse,
    call_generate_outlines,
)
12
from sglang.utils import dump_state_text, read_jsonl
Liangsheng Yin's avatar
Liangsheng Yin committed
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
from tqdm import tqdm

# there are some FSM bugs with json regex converted from pydantic model
# here use a string regex instead
# regex_string = build_regex_from_object(HarryPoterRole)
character_regex = (
    r"""\{\n"""
    + r"""    "name": "[\w\d\s]{1,16}",\n"""
    + r"""    "house": "(Gryffindor|Slytherin|Ravenclaw|Hufflepuff)",\n"""
    + r"""    "blood status": "(Pure-blood|Half-blood|Muggle-born)",\n"""
    + r"""    "occupation": "(student|teacher|auror|ministry of magic|death eater|order of the phoenix)",\n"""
    + r"""    "wand": \{\n"""
    + r"""        "wood": "[\w\d\s]{1,16}",\n"""
    + r"""        "core": "[\w\d\s]{1,16}",\n"""
    + r"""        "length": [0-9]{1,2}\.[0-9]{0,2}\n"""
    + r"""    \},\n"""
    + r"""    "alive": "(Alive|Deceased)",\n"""
    + r"""    "patronus": "[\w\d\s]{1,16}",\n"""
    + r"""    "bogart": "[\w\d\s]{1,16}"\n"""
    + r"""\}"""
)

35
36
37
38
39
40
41
42
43
44
city_regex = (
    r"""\{\n"""
    + r"""  "name": "[\w\d\s]{1,16}",\n"""
    + r"""  "country": "[\w\d\s]{1,16}",\n"""
    + r"""  "latitude": [-+]?[0-9]*\.?[0-9]{0,2},\n"""
    + r"""  "population": [-+]?[0-9]{1,9},\n"""
    + r"""  "top 3 landmarks": \["[\w\d\s]{1,16}", "[\w\d\s]{1,16}", "[\w\d\s]{1,16}"\]\n"""
    + r"""\}"""
)

Liangsheng Yin's avatar
Liangsheng Yin committed
45
46
# fmt: off
def character_gen(name, generate):
47
    s = name + " is a character in Harry Potter. Please fill in the following information about this character.\n"
Liangsheng Yin's avatar
Liangsheng Yin committed
48
49
50
51
    s += generate(s, max_tokens=256, regex=character_regex)
    return s
# fmt: on

52
53
54
55
56
57
58
59
60
# fmt: off
def city_gen(document, generate):
    s = "Please extract the information of a city from the following wikipedia page.\n"
    s += "Page begin.\n" + document + "Page end.\n"
    s += "Here is the name, country, and symbol of the city in JSON format.\n"
    s += generate(s, max_tokens=256, regex=city_regex)
    return s
# fmt: on

Liangsheng Yin's avatar
Liangsheng Yin committed
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86

@guidance
def character_maker(lm, name):
    regex_str_no_quote = r"[\w\d\s]+"
    regex_float = r"[0-9]+\.[0-9]+"
    lm += f"""\
    {name} is a character in Harry Potter. Please fill in the following information about him/her.
    {{
        "name": "{guidance.gen("name", max_tokens=16, regex=regex_str_no_quote)}",
        "house": "{guidance.select(options=['Gryffindor', 'Slytherin', 'Ravenclaw', 'Hufflepuff'], name='house')}",
        "blood status": "{guidance.select(options=['Pure-blood', 'Half-blood', 'Muggle-born'], name='blood status')}",
        "occupation": "{guidance.select(options=['student', 'teacher', 'auror', 'ministry of magic', 'death eater', 'order of the phoenix'], name='occupation')}",
        "wand": {{
            "wood": "{guidance.gen("wood", max_tokens=16, regex=regex_str_no_quote)}",
            "core": "{guidance.gen('core', max_tokens=16, regex=regex_str_no_quote)}",
            "length": {guidance.gen('length', max_tokens=10, regex=regex_float)}
        }},
        "alive": "{guidance.select(options=['Alive', 'Deceased'], name='alive')}",
        "patronus": "{guidance.gen('patronus', max_tokens=16, regex=regex_str_no_quote)}",
        "bogart": "{guidance.gen('bogart', max_tokens=16, regex=regex_str_no_quote)}"
    }}
    """

    return lm


87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
@guidance
def city_maker(lm, document):
    regex_str_no_quote = r"[\w\d\s]+"
    regex_float = r"[0-9]+\.[0-9]+"
    lm += f"""\
    Please extract the information of a city from the following wikipedia page.
    Page begin.
    {document}
    Page end.
    Here is the name, country, and symbol of the city in JSON format.
    {{
        "name": "{guidance.gen("name", max_tokens=16, regex=regex_str_no_quote)}",
        "country": "{guidance.gen("country", max_tokens=16, regex=regex_str_no_quote)}",
        "latitude": {guidance.gen("latitude", max_tokens=10, regex=regex_float)},
        "population": {guidance.gen("population", max_tokens=10, regex=r"[0-9]+")},
        "top 3 landmarks": [
            "{guidance.gen("landmark1", max_tokens=16, regex=regex_str_no_quote)}", "{guidance.gen("landmark2", max_tokens=16, regex=regex_str_no_quote)}", "{guidance.gen("landmark3", max_tokens=16, regex=regex_str_no_quote)}"
        ]
    }}
    """

    return lm


def bench_character(args):
Liangsheng Yin's avatar
Liangsheng Yin committed
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
    arguments = []
    with open(args.data_path, "r") as f:
        for line in f:
            arguments.append({"name": line.strip()})
    arguments = arguments[: args.num_jsons]

    states = [None] * len(arguments)

    # Select backend
    if args.backend == "vllm":
        url = f"{args.host}:{args.port}/generate"
        generate = partial(call_generate_outlines, url=url, temperature=0)

        def func(i):
            states[i] = character_gen(**arguments[i], generate=generate)

        get_one_answer = func
    elif args.backend == "guidance":
        model = guidance.models.LlamaCpp(
131
            args.llama_cpp_model_path,
Liangsheng Yin's avatar
Liangsheng Yin committed
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
            n_gpu_layers=-1,
            n_ctx=4096,
        )

        def func(i):
            lm = model + character_maker(**arguments[i])
            states[i] = lm

        get_one_answer = func
    else:
        raise ValueError(f"Invalid backend: {args.backend}")

    tic = time.time()
    if args.parallel == 1:
        for i in tqdm(range(len(arguments))):
            get_one_answer(i)
    else:
        with ThreadPoolExecutor(args.parallel) as executor:
            rets = executor.map(get_one_answer, list(range(len(arguments))))
            for _ in rets:
                pass

    latency = time.time() - tic

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
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
    return states, latency


def bench_city_doc(args):
    arguments = []
    for line in read_jsonl(args.data_path):
        arguments.append({"document": line["document"]})
    arguments = arguments[: args.num_jsons]

    states = [None] * len(arguments)

    # Select backend
    if args.backend == "vllm":
        url = f"{args.host}:{args.port}/generate"
        generate = partial(call_generate_outlines, url=url, temperature=0)

        def func(i):
            states[i] = city_gen(**arguments[i], generate=generate)

        get_one_answer = func
    elif args.backend == "guidance":
        model = guidance.models.LlamaCpp(
            args.llama_cpp_model_path,
            n_gpu_layers=-1,
            n_ctx=4096,
        )

        def func(i):
            lm = model + city_maker(**arguments[i])
            states[i] = lm

        get_one_answer = func
    else:
        raise ValueError(f"Invalid backend: {args.backend}")

    tic = time.time()
    if args.parallel == 1:
        for i in tqdm(range(len(arguments))):
            get_one_answer(i)
    else:
        with ThreadPoolExecutor(args.parallel) as executor:
            rets = executor.map(get_one_answer, list(range(len(arguments))))
            for _ in rets:
                pass

    latency = time.time() - tic

    return states, latency


def main(args):
    if args.mode == "character":
        args.data_path = "dataset.txt"
        states, latency = bench_character(args)
    elif args.mode == "city":
        args.data_path = "questions.jsonl"
        states, latency = bench_city_doc(args)

Liangsheng Yin's avatar
Liangsheng Yin committed
214
215
216
217
    # Compute accuracy
    print(f"Latency: {latency:.3f}")

    # Write results
218
    dump_state_text(f"tmp_output_{args.backend}_{args.mode}.txt", states)
Liangsheng Yin's avatar
Liangsheng Yin committed
219
220
221
222
223
224
225
226
227
228
229
230
231
232

    with open(args.result_file, "a") as fout:
        value = {
            "task": "json_fast_forward",
            "backend": args.backend,
            "latency": round(latency, 3),
            "num_jsons": args.num_jsons,
            "parallel": args.parallel,
        }
        fout.write(json.dumps(value) + "\n")


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
233
    parser.add_argument("--data-path", type=str)
Liangsheng Yin's avatar
Liangsheng Yin committed
234
    parser.add_argument("--num-jsons", type=int, default=50)
235
236
237
238
239
240
241
242
    parser.add_argument(
        "--mode", type=str, default="character", choices=["character", "city"]
    )
    parser.add_argument(
        "--llama-cpp-model-path",
        type=str,
        default="/home/ubuntu/model_weights/Llama-2-7b-chat-hf/ggml-model-f16.gguf",
    )
Liangsheng Yin's avatar
Liangsheng Yin committed
243
244
    args = add_common_other_args_and_parse(parser)
    main(args)