EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Lint]Style: Convert example to ruff format (#5863)

Browse Source 
### What this PR does / why we need it?
This PR fixes linting issues in the `example/` to align with the
project's Ruff configuration.

- vLLM version: v0.13.0
- vLLM main:
bde38c11df

Signed-off-by: root <root@LAPTOP-VQKDDVMG.localdomain>
Co-authored-by: root <root@LAPTOP-VQKDDVMG.localdomain>
This commit is contained in:
SILONG ZENG
2026-01-13 20:46:50 +08:00
committed by GitHub
parent f7b904641e
commit 78d5ce3e01
23 changed files with 678 additions and 1037 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
examples/offline_inference_npu_long_seq.py
View File

@@ -1,6 +1,6 @@
import argparse
import os
import time
import argparse
from vllm import LLM, SamplingParams
@@ -11,14 +11,14 @@ os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('--input_len', type=int, default=1024)
parser.add_argument('--output_len', type=int, default=128)
parser.add_argument('--bs', type=int, default=1)
parser.add_argument('--model_path', type=str, default="deepseek-ai/DeepSeek-V2-Lite")
parser.add_argument('--tp', type=int, default=2)
parser.add_argument('--pcp', type=int, default=2)
parser.add_argument('--dcp', type=int, default=1)
parser.add_argument('--iter_times', type=int, default=1)
parser.add_argument("--input_len", type=int, default=1024)
parser.add_argument("--output_len", type=int, default=128)
parser.add_argument("--bs", type=int, default=1)
parser.add_argument("--model_path", type=str, default="deepseek-ai/DeepSeek-V2-Lite")
parser.add_argument("--tp", type=int, default=2)
parser.add_argument("--pcp", type=int, default=2)
parser.add_argument("--dcp", type=int, default=1)
parser.add_argument("--iter_times", type=int, default=1)
args = parser.parse_args()
@@ -26,10 +26,10 @@ if __name__ == "__main__":
"The capital of France is",
"Hello, my name is Tom, I am",
"The president of United States is",
"AI future is"
"AI future is",
]
sampling_params = SamplingParams(temperature = 0.8, top_p = 0.95, max_tokens=args.output_len)
sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=args.output_len)
llm = LLM(
model=args.model_path,
trust_remote_code=True,
@@ -44,7 +44,7 @@ if __name__ == "__main__":
max_model_len=1024,
max_num_seqs=1,
block_size=128,
gpu_memory_utilization=0.9
gpu_memory_utilization=0.9,
)
t0 = time.time()
@@ -56,4 +56,4 @@ if __name__ == "__main__":
for i, output in enumerate(outputs):
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"req_num: {i}\nGenerated text: {generated_text!r}")
print(f"req_num: {i}\nGenerated text: {generated_text!r}")