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 11, 08:45 UTC
[Docs][API] Remove warning about LoRARequest being internal-only (#30774)
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Mark McLoughlin committed
Dec 16, 2025 at 16:35 UTC
66c3537e5df215d8095d7042b8e7abd51260393f
1 file changed
-5
vllm/lora/request.py
-5
@@ -14,11 +14,6 @@ class LoRARequest(
14
"""
15
Request for a LoRA adapter.
16
17
- Note that this class should be used internally. For online
18
- serving, it is recommended to not allow users to use this class but
19
- instead provide another layer of abstraction to prevent users from
20
- accessing unauthorized LoRA adapters.
21
-
17
lora_int_id must be globally unique for a given adapter.
18
This is currently not enforced in vLLM.
19
"""