Jiaxin Shan

### 🚀 Feature Description and Motivation service discovery is commonly misconfigured by users. However, we do not have every straightforward ways to help user diagnose the problem. The most easiest...

[Discussion] Simplify AIBrix deployment by removing Envoy Gateway

2

### 🚀 Feature Description and Motivation Today AIBrix recommends/ships Envoy Gateway, but we typically run a `single` gateway instance. Envoy Gateway adds installation and controller complexity that many users don’t...

### 🚀 Feature Description and Motivation Now, we need to launch kubernetes jobs and host GPU models. In order to support broader customers. We need to consider other resource providers....

### 🚀 Feature Description and Motivation see discussion here https://github.com/vllm-project/aibrix/pull/1639#discussion_r2418152646 Let's build better abstraction instead of directly reference a redis client. At the same time, storage has a redis implementation...

engine prefix should be provided by user and we should not amend `vllm:`

2

### 🐛 Describe the bug ``` W0930 18:13:41.031286 1 fetcher.go:99] Failed to fetch metric vllm:gpu_cache_usage_perc from pod default/mock-llama2-7b-7cc98b7f5f-764t4: metric vllm:gpu_cache_usage_perc not found in central registry. Returning zero value. ``` ###...

### 🚀 Feature Description and Motivation https://github.com/vllm-project/aibrix/pull/1639#discussion_r2417964859 The current user management API (/CreateUser, /ReadUser, etc., all using POST) is a direct migration from the previous Go service. While functional, it...

hpa reconcile keep generating the new recommendation

4

### 🐛 Describe the bug 1. When we update the hpa configuration, it will enqueue the objects and immediately generate the new recommendations. 2. Controller normally updates the CR object...

Add Circuit Breaker Policy for HPA on Bad Metrics

2

### 🚀 Feature Description and Motivation Currently, when PodAutoscaler (HPA/KPA/APA) receives abnormal or invalid metrics (e.g., NaN, outliers, sudden spikes) or unexpected behaviors like error rate going up etc, it...

[Feat] Support StormService pause rollout in upgrade

4

## Pull Request Description [Feat] Support StormService pause rollout in upgrade * Update stormservice golang client * Improve the test coverage * Refactor the API to support manual resume ##...

### 🚀 Feature Description and Motivation Our autoscaling framework already has multiple MetricFetcher implementations: - RestMetricsFetcher → direct pod /metrics endpoint - ResourceMetricsFetcher → Kubernetes resource metrics (cpu, memory) -...