EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

adapt to sglang v0.5.2rc1 on dcu

Browse Source
This commit is contained in:
maxiao
2025-09-04 15:56:33 +08:00
commit 909abb58f5
2320 changed files with 489411 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

88
benchmark/json_jump_forward/README.md Normal file
View File

@@ -0,0 +1,88 @@
## Run benchmark
### Dependencies
```
llama_cpp_python 0.2.38
guidance 0.1.10
vllm 0.2.7
outlines 0.0.25
```
### Build dataset
When benchmarking long document information retrieval, run the following command to build the dataset:
```bash
pip install wikipedia
python3 build_dataset.py
```
### Benchmark sglang
Run Llama-7B
```bash
python3 -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000
```
Benchmark Character Generation
```bash
python3 bench_sglang.py --mode character
```
Benchmark City Information Retrieval
```bash
python3 bench_sglang.py --mode city
```
### Benchmark Outlines + vLLM
Run Llama-7B
```bash
python3 -m outlines.serve.serve --tokenizer-mode auto --model meta-llama/Llama-2-7b-chat-hf --disable-log-requests --port 21000
```
Benchmark Character Generation
```bash
python3 bench_other.py --mode character --backend outlines
```
Benchmark City Information Retrieval
```bash
python3 bench_other.py --mode city --backend outlines
```
### Benchmark guidance
Run Llama-7B and benchmark character generation
```bash
python3 bench_other.py --mode character --backend guidance --parallel 1 --n-ctx 4096 --model-path path/to/gguf
```
Run Llama-7B and benchmark city information retrieval
```bash
python3 bench_other.py --mode city --backend guidance --parallel 1 --n-ctx 4096 --model-path path/to/gguf
```
### Benchmark lmql
Run Llama-7B and benchmark character generation
```
python3 bench_other.py --mode character --backend lmql --parallel 1
```
Run Llama-7B and benchmark city information retrieval
```
python3 bench_other.py --mode city --backend lmql --parallel 1
```

288
benchmark/json_jump_forward/bench_other.py Normal file
View File

@@ -0,0 +1,288 @@
import argparse
import json
import time
from concurrent.futures import ThreadPoolExecutor
from functools import partial
import guidance
from tqdm import tqdm
from sglang.test.test_utils import add_common_other_args_and_parse, get_call_generate
from sglang.utils import dump_state_text, read_jsonl
# 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"""\}"""
)
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"""\}"""
)
# fmt: off
def character_gen(name, generate):
s = name + " is a character in Harry Potter. Please fill in the following information about this character.\n"
s += generate(s, max_tokens=256, regex=character_regex)
return s
# fmt: on
# 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
@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 this character.
{{
"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
async def call_generate_lmql(
prompt, temperature, max_tokens, regex, max_len=4096, model=None, **kwargs
):
assert model is not None
import lmql
@lmql.query(model=model)
async def program(question, max_tokens, regex):
'''lmql
"""{question}[ANSWER]""" where len(TOKENS(ANSWER)) < max_tokens and REGEX(ANSWER, regex)
return ANSWER
'''
return await program(
question=prompt,
temperature=temperature,
max_tokens=max_tokens,
max_len=max_len,
regex=regex,
**kwargs,
)
@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):
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 == "outlines":
call_generate = partial(get_call_generate(args), temperature=0)
def get_one_answer(i):
states[i] = character_gen(**arguments[i], generate=call_generate)
elif args.backend == "guidance":
model = guidance.models.LlamaCpp(
args.model_path,
n_gpu_layers=-1,
n_ctx=args.n_ctx,
)
def get_one_answer(i):
lm = model + character_maker(**arguments[i])
states[i] = lm
elif args.backend == "lmql":
import asyncio
import lmql
model = lmql.model(args.model_path, endpoint=f"{args.host}:{args.port}")
call_generate = partial(
call_generate_lmql,
model=model,
max_tokens=256,
regex=character_regex,
)
async def get_one_answer_async(i):
states[i] = await call_generate(prompt=arguments[i]["name"], temperature=0)
else:
raise ValueError(f"Invalid backend: {args.backend}")
tic = time.perf_counter()
if args.backend != "lmql":
if args.parallel == 1:
for i in tqdm(range(len(arguments))):
get_one_answer(i)
else:
with ThreadPoolExecutor(args.parallel) as executor:
rets = list(
tqdm(
executor.map(get_one_answer, list(range(len(arguments)))),
total=len(arguments),
)
)
for _ in rets:
pass
else:
batches = []
for i in range(0, len(arguments), args.parallel):
batches.append(list(range(i, min(i + args.parallel, len(arguments)))))
loop = asyncio.get_event_loop()
for bt in tqdm(batches):
loop.run_until_complete(
asyncio.gather(*[get_one_answer_async(i) for i in bt])
)
latency = time.perf_counter() - tic
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 == "outlines":
call_generate = partial(get_call_generate(args), temperature=0)
def get_one_answer(i):
states[i] = city_gen(**arguments[i], generate=call_generate)
elif args.backend == "guidance":
model = guidance.models.LlamaCpp(
args.model_path,
n_gpu_layers=-1,
n_ctx=args.n_ctx,
)
def get_one_answer(i):
lm = model + city_maker(**arguments[i])
states[i] = lm
else:
raise ValueError(f"Invalid backend: {args.backend}")
tic = time.perf_counter()
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.perf_counter() - 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)
# Compute accuracy
print(f"Latency: {latency:.3f}")
# Write results
dump_state_text(f"tmp_output_{args.backend}_{args.mode}.txt", states)
with open(args.result_file, "a") as fout:
value = {
"task": "json_jump_forward",
"backend": args.backend,
"latency": round(latency, 3),
"num_jsons": args.num_jsons,
"mode": args.mode,
"parallel": args.parallel,
}
fout.write(json.dumps(value) + "\n")
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--data-path", type=str)
parser.add_argument("--num-jsons", type=int, default=50)
parser.add_argument(
"--mode", type=str, default="character", choices=["character", "city"]
)
args = add_common_other_args_and_parse(parser)
main(args)

143
benchmark/json_jump_forward/bench_sglang.py Normal file
View File

@@ -0,0 +1,143 @@
import argparse
import json
import time
import sglang as sgl
from sglang.test.test_utils import (
add_common_sglang_args_and_parse,
select_sglang_backend,
)
from sglang.utils import dump_state_text, read_jsonl
# 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"""\}"""
)
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"""\}"""
)
# fmt: off
@sgl.function
def character_gen(s, name):
s += name + " is a character in Harry Potter. Please fill in the following information about this character.\n"
s += sgl.gen("json_output", max_tokens=256, regex=character_regex)
# fmt: on
# fmt: off
@sgl.function
def city_gen(s, document):
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 += sgl.gen("json_output",max_tokens=256, regex=city_regex)
# fmt: on
def bench_city_doc(args):
arguments = []
for line in read_jsonl(args.data_path):
arguments.append({"document": line["document"]})
arguments = arguments[: args.num_jsons]
# Select backend
backend = select_sglang_backend(args)
sgl.set_default_backend(backend)
# Run requests
tic = time.perf_counter()
states = city_gen.run_batch(
arguments,
temperature=0,
num_threads=args.parallel,
progress_bar=True,
)
latency = time.perf_counter() - tic
return states, latency
def bench_character(args):
arguments = []
with open(args.data_path, "r") as f:
for line in f:
arguments.append({"name": line.strip()})
arguments = arguments[: args.num_jsons]
# Select backend
backend = select_sglang_backend(args)
sgl.set_default_backend(backend)
# Run requests
tic = time.perf_counter()
states = character_gen.run_batch(
arguments,
temperature=0,
num_threads=args.parallel,
progress_bar=True,
)
latency = time.perf_counter() - 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)
# Compute accuracy
print(f"Latency: {latency:.3f}")
# Write results
dump_state_text(f"tmp_output_{args.backend}_{args.mode}.txt", states)
with open(f"{args.backend}_{args.mode}.json", "w") as fout:
for state in states:
fout.write(state["json_output"] + "\n")
with open(args.result_file, "a") as fout:
value = {
"task": "json_jump_forward",
"backend": args.backend,
"latency": round(latency, 3),
"num_jsons": args.num_jsons,
"mode": args.mode,
"parallel": args.parallel,
}
fout.write(json.dumps(value) + "\n")
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--data-path", type=str)
parser.add_argument("--num-jsons", type=int, default=50)
parser.add_argument(
"--mode", type=str, default="character", choices=["character", "city"]
)
args = add_common_sglang_args_and_parse(parser)
main(args)

58
benchmark/json_jump_forward/build_dataset.py Normal file
View File

@@ -0,0 +1,58 @@
import json
import transformers
import wikipedia
model_path = "meta-llama/Llama-2-7b-chat-hf"
t = transformers.AutoTokenizer.from_pretrained(model_path)
city_names = [
"los angles",
"london",
"tokyo",
"beijing",
"singapore",
"paris",
"dubai",
"sydney",
"moscow",
"rome",
"toronto",
"rio de janeiro",
"istanbul",
"berlin",
"auckland",
"buenos aires",
"mexico city",
"mumbai",
"seoul",
"bangkok",
"cairo",
"athens",
"jerusalem",
]
def get_content(city_name):
content = str(wikipedia.page(city_name).content)
content = content.replace("\n\n", "\n")
tokens = t.encode(content)
expected_tokens = 3000
truncate_len = int((expected_tokens / len(tokens)) * len(content))
truncate_content = content[:truncate_len]
truncate_tokens = t.encode(truncate_content)
# Count token
print(
f"city_name: {city_name}, #tokens: {len(tokens)}, #truncate tokens: {len(truncate_tokens)}"
)
return truncate_content
if __name__ == "__main__":
with open("questions.jsonl", "w") as fout:
for city_name in city_names:
truncate_content = get_content(city_name)
fout.write(json.dumps({"document": truncate_content}) + "\n")

50
benchmark/json_jump_forward/dataset.txt Normal file
View File

@@ -0,0 +1,50 @@
Harry Potter
Hermione Granger
Ron Weasley
Albus Dumbledore
Severus Snape
Rubeus Hagrid
Draco Malfoy
Ginny Weasley
Fred Weasley
George Weasley
Percy Weasley
Sirius Black
Remus Lupin
Neville Longbottom
Luna Lovegood
Cedric Diggory
Cho Chang
Lord Voldemort
Minerva McGonagall
Filius Flitwick
Dolores Umbridge
Bellatrix Lestrange
Lucius Malfoy
Molly Weasley
Arthur Weasley
Nymphadora Tonks
Dobby
Moaning Myrtle
Peter Pettigrew
Alastor 'Mad-Eye' Moody
Horace Slughorn
Vernon Dursley
Petunia Dursley
Dudley Dursley
Argus Filch
Sybill Trelawney
Gilderoy Lockhart
Fleur Delacour
Viktor Krum
Bill Weasley
Oliver Wood
Cornelius Fudge
Barty Crouch Sr.
Barty Crouch Jr.
Kingsley Shacklebolt
Quirinus Quirrell
Nearly Headless Nick
Aunt Marge
Griphook
Ludo Bagman