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 8, 17:45 UTC
fix description in plugin_system.md (#33999)
果冻虾仁 committed
Feb 7, 2026 at 11:37 UTC
6f7adc533a3ad6b45d8e5a92cfa2e0094daa702b
1 file changed
+1
-1
docs/design/plugin_system.md
+1
-1
@@ -24,7 +24,7 @@ vLLM's plugin system uses the standard Python `entry_points` mechanism. This mec
24
["register_dummy_model = vllm_add_dummy_model:register"]
25
})
26
27
- # inside `vllm_add_dummy_model.py` file
27
+ # inside `vllm_add_dummy_model/__init__.py` file
28
def register():
29
from vllm import ModelRegistry
30