aibrix

aibrix copied to clipboard

Pod status in kubectl get pod is wrong

3

### 🐛 Describe the bug This is the screenshot of kubectl get pod. You can see the STATUS is 'running' even if the pod is not actually ready (see the...

gangmuk

### 🚀 Feature Description and Motivation  Varun raise great point on the checking logic 1. consider number of containers 2. Second, better to have a second loop to match...

Jeffwan

failures in release pipeline

2

### 🐛 Describe the bug 1. release actions are not working  2. pushing artifacts failed  ### Steps to Reproduce _No response_ ### Expected behavior _No response_ ### Environment...

Jeffwan

Model adapter controller connect: Connection refused failed for /v1/models lora fetching.

1

### 🐛 Describe the bug  Let's follow up on how to better support such case. ### Steps to Reproduce _No response_ ### Expected behavior _No response_ ### Environment _No...

Jeffwan

### 🐛 Describe the bug We should mitigate such unhelpful messages by adjusting the debug level etc  ### Steps to Reproduce _No response_ ### Expected behavior _No response_ ###...

Jeffwan

Introduce wait time or retry before moving adapter to another pod if that pod is not ready

2

### 🚀 Feature Description and Motivation This is a follow up issue from https://github.com/aibrix/aibrix/pull/257#issuecomment-2383841118 from @varungup90 "Here retry will be for model adapter reconcile. For 5 retries, with 5 second...

Jeffwan

Should we switch to different pod if model adapter load is failing for x times?

4

### Scenario 1 model adapter load is failing infinitely I added an error in model load. As expected model is not loading. But problem is that, in model adapter it...

varungup90

Support multiple Lora adapter replicas

5

### 🚀 Feature Description and Motivation In the initial version, to simplify the the model adapter autoscaling, we determine to support only 1 replica in the CRD. Technically, we should...

Jeffwan

### 🐛 Describe the bug  ### Steps to Reproduce _No response_ ### Expected behavior _No response_ ### Environment _No response_

varungup90

### 🚀 Feature Description and Motivation  this change blocks the CI and release pipeline. I temporarily change back but this needs to be changed later.  ### Use Case...

Jeffwan