A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 5, 07:15 UTC
[Misc] Update deprecation warning for --model flag (#39518)
Signed-off-by: Ziying Tao <tzzying@outlook.com>
z1ying committed
Apr 10, 2026 at 23:25 UTC
a3e750c0a587e64169736b74e21e3592c618ef11
1 file changed
+1
-1
vllm/utils/argparse_utils.py
+1
-1
@@ -192,7 +192,7 @@ class FlexibleArgumentParser(ArgumentParser):
192
"With `vllm serve`, you should provide the model as a "
193
"positional argument or in a config file instead of via "
194
"the `--model` option. "
195
- "The `--model` option will be removed in v0.13."
195
+ "The `--model` option will be removed in a future version."
196
)
197
198
if args[model_idx] == "--model":