biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Convert examples to ruff-format (#18400)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-05-26 17:57:54 +01:00
committed by GitHub
parent e7523c2e03
commit 27bebcd897
83 changed files with 2529 additions and 2405 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
examples/offline_inference/automatic_prefix_caching.py
View File

@@ -16,13 +16,16 @@ but ask different questions.
Run:
python examples/offline_inference/automatic_prefix_caching.py
"""
import time
from vllm import LLM, SamplingParams
# ruff: noqa: E501
# A prompt containing a large markdown table. The table is randomly generated by GPT-4.
LONG_PROMPT = "You are a helpful assistant in recognizes the content of tables in markdown format. Here is a table as follows.\n# Table\n" + """
LONG_PROMPT = (
"You are a helpful assistant in recognizes the content of tables in markdown format. Here is a table as follows.\n# Table\n"
+ """
| ID | Name | Age | Occupation | Country | Email | Phone Number | Address |
|-----|---------------|-----|---------------|---------------|------------------------|----------------|------------------------------|
| 1 | John Doe | 29 | Engineer | USA | john.doe@example.com | 555-1234 | 123 Elm St, Springfield, IL |
@@ -56,6 +59,7 @@ LONG_PROMPT = "You are a helpful assistant in recognizes the content of tables i
| 29 | Amy White | 33 | Musician | New Zealand | amy.w@example.com | 555-5658 | 159 Maple St, Wellington, NZ |
| 30 | Ben Black | 38 | Chef | Ireland | ben.b@example.com | 555-7870 | 246 Fir St, Waterford, IE |
"""
)
def get_generation_time(llm, sampling_params, prompts):
@@ -72,7 +76,7 @@ def get_generation_time(llm, sampling_params, prompts):
def main():
# set enable_prefix_caching=True to enable APC
llm = LLM(model='lmsys/longchat-13b-16k', enable_prefix_caching=True)
llm = LLM(model="lmsys/longchat-13b-16k", enable_prefix_caching=True)
sampling_params = SamplingParams(temperature=0, max_tokens=100)
@@ -80,8 +84,8 @@ def main():
get_generation_time(
llm,
sampling_params,
LONG_PROMPT +
"Question: what is the age of John Doe? Your answer: The age of John Doe is ",
LONG_PROMPT
+ "Question: what is the age of John Doe? Your answer: The age of John Doe is ",
)
# Querying the age of Zack Blue
@@ -89,8 +93,8 @@ def main():
get_generation_time(
llm,
sampling_params,
LONG_PROMPT +
"Question: what is the age of Zack Blue? Your answer: The age of Zack Blue is ",
LONG_PROMPT
+ "Question: what is the age of Zack Blue? Your answer: The age of Zack Blue is ",
)