List of Embedding Models in DKubeX Embedding Model Catalog

Serving Models and Open-source LLMs

The following list contains the embedding models which are currently registered with the DKubeX embedding model catalog on the current version of DKubeX (DKubeX v0.8.6.3).

Embedding Models registered on the DKubeX Embedding Model Catalog

Embedding Model Name	Accelerator	Max Total Tokens	Number of GPUs needed
BAAI--bge-large-en-v1-5	A10	512	0
BAAI--bge-m3	A10	512	0
thenlper--gte-large	A10	512	0

These embedding models can be deployed on the DKubeX platform without using any config files provided the resource and permission requirements are met. You can deploy these embedding models on DKubeX using local resources or using cloud resources using SkyPilot. For more information on deploying embedding models, go to the appropriate page provided below.

Deploying Embedding Models using Local Resources

./serving/emb_deploy.html

Deploying Embedding Models using SkyPilot

./skypilot/emb-deployment-with-skypilot.html