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 7, 06:30 UTC
[Docs] Upgrade dynamic LoRA warning to admonition block (#35218)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Russell Bryant committed
Mar 4, 2026 at 13:01 UTC
2f2c1d73a745d8a38d1a21a5865a7d53d8d616b7
1 file changed
+2
-1
docs/features/lora.md
+2
-1
@@ -106,7 +106,8 @@ curl http://localhost:8000/v1/completions \
106
107
In addition to serving LoRA adapters at server startup, the vLLM server supports dynamically configuring LoRA adapters at runtime through dedicated API endpoints and plugins. This feature can be particularly useful when the flexibility to change models on-the-fly is needed.
108
109
-Note: Enabling this feature in production environments is risky as users may participate in model adapter management.
109
+!!! warning
110
+ This feature comes with security risks. It should not be used in production unless it is an isolated, fully trusted environment.
111
112
To enable dynamic LoRA configuration, ensure that the environment variable `VLLM_ALLOW_RUNTIME_LORA_UPDATING`
113
is set to `True`.