Jiaxin Shan

### 🚀 Feature Description and Motivation AFN is super popular now and vLLM community is spend efforts on the support. In Bytedance, it also have some practice on AFN. Let's...

### Summary There're some feedback reviewing the current doc site - Production Readiness Gap - Comprehensive Troubleshooting. current FAQ page only have 1-2 cases.. - Performance Tuning - Production Deployment...

[Call for Adopters] Tell us how you use AIBrix 🚀

2

### 🚀 Feature Description and Motivation We’re collecting real-world AIBrix usage to help guide the roadmap and (optionally) showcase adopters on aibrix.ai and the README. **How we’ll use this** -...

batch api doesn't work as expected.

2

### 🐛 Describe the bug I feel it does work as expected.. I can not find jobs, the model name is actually wrong but executor seems process the inputs. metadata...

### 🚀 Feature Description and Motivation draft roadmap ### Use Case N/A ### Proposed Solution N/A

### 🐛 Describe the bug this is due to metadata service migration. we should support both empty and / suffix. to make sure the compatibility ### Steps to Reproduce curl...

### 🚀 Feature Description and Motivation Follow up of https://github.com/vllm-project/aibrix/pull/1738 step 1 ``` helm install eg oci://docker.io/envoyproxy/gateway-helm --version v1.2.8 -n envoy-gateway-system --create-namespace ``` step 2 ``` # patch the configuration...

Support DeepSeek/DeepSeek-OCR

5

### 🚀 Feature Description and Motivation https://docs.vllm.ai/projects/recipes/en/latest/DeepSeek/DeepSeek-OCR.html#running-deepseek-ocr 1. this file doesn't have api interface, user need to leverage LLM class 2. it doesn't have batch api support. ### Use Case...

Support predictive autoscaling for LLM inference

8

### 🚀 Feature Description and Motivation We used to do a lot of work around reactive autoscaling, however, the model bootstrap still take looks long time. Instead of traditional autoscaling,...