Jiaxin Shan
Jiaxin Shan
Due to the limited bandwidth, I will remove these two items from v0.3.0 and move to v0.4.0 - Model centric deployment - [ ] https://github.com/vllm-project/aibrix/issues/302 - Batch workloads optimization -...
@Venkat2811 not yet. I plan to start the v0.4.0 release process once v0.3.0 approaches release status, likely sometime in early May
AIBrix v0.3.0 has been officially released! https://github.com/vllm-project/aibrix/releases/tag/v0.3.0 I am closing this issue. We're now starting preparations for v0.4.0. If you have a feature wish list or suggestions, feel free to...
Seems I applied to different env because of my kube-context setting are different in two windows.
@nwangfw Please document the steps to build vidur based container (for heterogenous feature only) and make sure it won't break. I will remove this from v0.2.0 release but keep this...
this won't affect functionality and would be a low priority item at this moment. I moved to v0.3.0
https://github.com/vllm-project/aibrix/pull/1472 has addressed this issue.
@xieus this is a constraints on the scheduling. single lora model adapter can be scheduled to the pod no more than 1 replica. 2 replicas on single pod won't be...
#205 becomes a large change and I notice there're some edge cases needs to cover. I will postpone this feature to rc3.
It takes some time to refactor the current code base to improve the extensibility for such changes. I already move some refactor codes changes from #205 to #260 . This...