From b16828a0f592ee72dec60d12a523b19f0320366e Mon Sep 17 00:00:00 2001 From: Benoit Chevallier-Mames Date: Mon, 8 Apr 2024 18:44:46 +0200 Subject: [PATCH] reviews (to be squashed) --- concrete-ml-inference-on-endpoints-fhe.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/concrete-ml-inference-on-endpoints-fhe.md b/concrete-ml-inference-on-endpoints-fhe.md index c77200d0957..971107b9a07 100644 --- a/concrete-ml-inference-on-endpoints-fhe.md +++ b/concrete-ml-inference-on-endpoints-fhe.md @@ -147,7 +147,7 @@ Of course, this is just an example of the entrypoint's usage. Developers are enc ### Under the hood -Please note that all of this is done thanks to the flexibility of [custom handlers](https://huggingface.co/docs/inference-endpoints/en/guides/custom_handler) and we express our gratitude to the Hugging Face developers for offering such flexibility. The mechanism is defined in `handler.py`. As explained in the Hugging Face documentation, you can define the `__call__` method of `EndpointHandler` pretty much as you want: In our case, we have defined a `method` parameter, which can be `save_key` (to save FHE evaluation keys), `append_key` (to save FHE evaluation keys piece by piece if the key is too large to be sent in one single call) and finally `inference` (to run FHE inferences). These methods are used to set the evaluation key once, and then run all the inferences, one by one, as seen in `play_with_endpoint.py`. +Please note that all of this is done thanks to the flexibility of [custom handlers](https://huggingface.co/docs/inference-endpoints/en/guides/custom_handler), and we express our gratitude to the Hugging Face developers for offering such flexibility. The mechanism is defined in `handler.py`. As explained in the Hugging Face documentation, you can define the `__call__` method of `EndpointHandler` pretty much as you want: In our case, we have defined a `method` parameter, which can be `save_key` (to save FHE evaluation keys), `append_key` (to save FHE evaluation keys piece by piece if the key is too large to be sent in one single call) and finally `inference` (to run FHE inferences). These methods are used to set the evaluation key once and then run all the inferences, one by one, as seen in `play_with_endpoint.py`. ### Limits