-
I have downloaded LLAMA 3.2 1B Model from Hugging face with optimum-cli
optimum-cli export openvino --model meta-llama/Llama-3.2-1B-Instruct llama3.2-1b/1
Below are files downloaded
!…
-
TensorFlow Model serving in Connect was deprecated as of 2022.09.0 and removed as of 2023.01.0.
We recommend that folks use an API framework like [Plumber](https://tensorflow.rstudio.com/guides/de…
-
This is not an issue. We are currently working on developing a scalable architecture for our ranking system using Feast. As a backend, we are utilizing GCP for the offline store and Redis for the onli…
-
/kind feature
**Describe the solution you'd like**
[A clear and concise description of what you want to happen.]
Add a sample of MMS using a custom model server similar to [sklearn](https://githu…
-
Mlflow supports the logging of SparkML models using the Mleap persistence mechanism. However, The mlflow.mleap.log_model() does not save the pyfunc() model flavour for Mleap serialized models. When I …
-
https://docs.google.com/document/d/1sJEgsDWWCUF9XfZXo-Qwk-Y1Mzk-Rs5QsAqwERFBCIg/edit?ts=607d5d5d
-
**Please fill in this feature request template to ensure a timely and thorough response.**
## Willingness to contribute
The MLflow Community encourages new feature contributions. Would you or anot…
-
/kind bug
**What steps did you take and what happened:**
[A clear and concise description of what the bug is.]
1. Create a InferenceService with single Predictor.
2. Kserve controller successf…
-
/kind bug
### **What steps did you take and what happened:**
I am trying to start quick-start example with sklearn-iris-predictor.
_Problem:_ webhook that is called when I create InferenceServ…
-
### 🚀 The feature, motivation and pitch
There are huge potential in more advanced load balancing strategies tailored for the unique characteristics of AI inference, compared to basic strategies such …