# PEFT + Inference **URL:** \ **Category:** Inference Endpoints on the Hub\ **Created:** [March 7, 2023, 4:33pm UTC](https://discuss.huggingface.co/t/peft-inference/33268 "2023-03-07T16:33:19Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![anon29941377](https://avatars.discourse-cdn.com/v4/letter/a/e495f1/32.png) [@anon29941377](https://discuss.huggingface.co/u/anon29941377)\ **Post date:** [March 7, 2023, 4:33pm UTC](https://discuss.huggingface.co/t/peft-inference/33268/1 "2023-03-07T16:33:19Z")
Is there a way to get PEFT to work with inference endpoints? Ideally, we should be able to support multiple PEFT models with a common inference endpoint for the base model. ---
**Author:** ![usholanb](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/usholanb/32/18137_2.png) [@usholanb](https://discuss.huggingface.co/u/usholanb)\ **Post date:** [August 1, 2023, 11:22am UTC](https://discuss.huggingface.co/t/peft-inference/33268/2 "2023-08-01T11:22:55Z")
any updates here? ---
**Author:** ![osanseviero](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/osanseviero/32/38738_2.png) [@osanseviero](https://discuss.huggingface.co/u/osanseviero)\ **Post date:** [August 15, 2023, 9:44am UTC](https://discuss.huggingface.co/t/peft-inference/33268/3 "2023-08-15T09:44:18Z")
You could configure a custom handler that allows you to specify code to load the model and its adapters [Create custom Inference Handler](https://huggingface.co/docs/inference-endpoints/guides/custom_handler) ---
**Author:** ![iarbel](https://avatars.discourse-cdn.com/v4/letter/i/3da27b/32.png) [@iarbel](https://discuss.huggingface.co/u/iarbel)\ **Post date:** [January 15, 2024, 9:19am UTC](https://discuss.huggingface.co/t/peft-inference/33268/4 "2024-01-15T09:19:22Z")
How can we use it text-generation-inference? I assume that just loading it through a custom handler will serve it via transformers, no?