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

Fix and simplify deprecated=True CLI kwarg (#17781)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-05-07 16:51:06 +01:00
committed by GitHub
parent be8ff88e66
commit 646a31e51e
4 changed files with 27 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
examples/offline_inference/basic/generate.py
View File

@@ -7,9 +7,8 @@ from vllm.utils import FlexibleArgumentParser
def create_parser():
parser = FlexibleArgumentParser()
# Add engine args
engine_group = parser.add_argument_group("Engine arguments")
EngineArgs.add_cli_args(engine_group)
engine_group.set_defaults(model="meta-llama/Llama-3.2-1B-Instruct")
EngineArgs.add_cli_args(parser)
parser.set_defaults(model="meta-llama/Llama-3.2-1B-Instruct")
# Add sampling params
sampling_group = parser.add_argument_group("Sampling parameters")
sampling_group.add_argument("--max-tokens", type=int)