issues
search
Azure
/
kaito
Kubernetes AI Toolchain Operator
MIT License
344
stars
34
forks
source link
Add adapter support for inference
#446
Open
Fei-Guo
opened
1 month ago
Fei-Guo
commented
1 month ago
Add new APIs in workspace CRD
Change inference_api.py to allow loading multiple adapters together with the raw model weight files.
Change workspace controller to manage the life cycle of the inference adapters (hosted in init containers).