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 14, 05:30 UTC
[CI Bugfix] Fix CI by fully removing --enable-prompt-adapter (#23284)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Aug 20, 2025 at 20:18 UTC
bbea1cefdd1a29b53355b1655f5d2ae343921f85
1 file changed
-6
vllm/engine/arg_utils.py
-6
@@ -888,12 +888,6 @@ class EngineArgs:
888
parser.add_argument('--disable-log-stats',
889
action='store_true',
890
help='Disable logging statistics.')
891
- parser.add_argument('--enable-prompt-adapter',
892
- action='store_true',
893
- deprecated=True,
894
- help='[DEPRECATED] Prompt adapter has been '
895
- 'removed. Setting this flag to True or False'
896
- ' has no effect on vLLM behavior.')
891
892
return parser
893