Dengcheng Zhu

Fix envoy, gateway, and quickstart pd-model images

1

## Pull Request Description Currently envoy and gateway are pointing to envoyproxy namespace. They should be under aibrix ns. The quickstart pd-model image is referring to a non-existent image. Update...

Gateway not honoring port labeling

2

### 🐛 Describe the bug Description: StormService has the following setting. But gateway log shows: dial tcp 192.168.0.204:8000: connect: connection refused. ``` - name: prefill replicas: 2 stateful: true template:...

### 🚀 Feature Description and Motivation Currently AIBrix KVCache and routing tests are using separate images. Using a single image to reduce maintenance overhead and provide cleaner dev/test vehicle. ###...

Long StormService name causing pod not showing up in default namespace

1

### 🐛 Describe the bug 'kubectl get pod' shows no related pods. ### Steps to Reproduce 1. Deploy sglang or vllm 2p2d tp2 for Qwen3-32B. 2. kubectl get pod ###...

### 🐛 Describe the bug * prefillers throw the following exception. * The prefillers and decoders are still able to work in the 2nd test. ### Steps to Reproduce 1....

### 🐛 Describe the bug During benchmark, prefillers complain: ERROR 11-19 10:12:21 [distributed/.../v1/nixl_connector.py:1068] Potentially invalid KV blocks for unrecognized request chatcmpl-129a69c8-cd1a-40e0-aa3e-94662fd8cc2b were retrieved by a decode worker. They may have...

### 🐛 Describe the bug 2p2d error logs: - P0 log: ib_device.c:1380 UCX ERROR ibv_create_ah(dlid=49152 sl=0 port=1 src_path_bits=0 dgid=fe80::9e63:c0ff:fe73:bf12 flow_label=0xffffffff sgid_index=0 traffic_class=0) for UD mlx5 connect on mlx5_1 failed: No...

### 🐛 Describe the bug Pod log says: ib_mlx5dv_md.c:1100 UCX ERROR mlx5_1: ibv_modify_qp(UMR QP 0x2c5c) failed to modify to RTR: No such device ### Steps to Reproduce 1. Deploy sglang...