GTEdgeAI/gt-ai-os-community
3
0
Fork 0
Code Issues Packages Releases Wiki Activity

Update README.md
Some checks failed
Build and Push Multi-Arch Docker Images / Build control-panel-backend (amd64) (push) Has been cancelled
Build and Push Multi-Arch Docker Images / Build control-panel-frontend (amd64) (push) Has been cancelled
Build and Push Multi-Arch Docker Images / Build resource-cluster (amd64) (push) Has been cancelled
Build and Push Multi-Arch Docker Images / Build tenant-app (amd64) (push) Has been cancelled
Build and Push Multi-Arch Docker Images / Build tenant-backend (amd64) (push) Has been cancelled
Build and Push Multi-Arch Docker Images / Build control-panel-backend (arm64) (push) Has been cancelled
Build and Push Multi-Arch Docker Images / Build control-panel-frontend (arm64) (push) Has been cancelled
Build and Push Multi-Arch Docker Images / Build resource-cluster (arm64) (push) Has been cancelled
Build and Push Multi-Arch Docker Images / Build tenant-app (arm64) (push) Has been cancelled
Build and Push Multi-Arch Docker Images / Build tenant-backend (arm64) (push) Has been cancelled
Build and Push Multi-Arch Docker Images / Create multi-arch manifest for control-panel-backend (push) Has been cancelled
Build and Push Multi-Arch Docker Images / Create multi-arch manifest for control-panel-frontend (push) Has been cancelled
Build and Push Multi-Arch Docker Images / Create multi-arch manifest for resource-cluster (push) Has been cancelled
Build and Push Multi-Arch Docker Images / Create multi-arch manifest for tenant-app (push) Has been cancelled
Build and Push Multi-Arch Docker Images / Create multi-arch manifest for tenant-backend (push) Has been cancelled

Browse Source
This commit is contained in:
Daniel
2026-01-10 03:37:23 +00:00
parent 5eb27b5d40
commit 4e6db17940
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -38,7 +38,7 @@ Note that the install scripts are unique for each OS and hardware architecture.
Carefully choose the correct installation script for your host. Carefully choose the correct installation script for your host.
## Embedding model GPU acceleration: ## Embedding model GPU acceleration:
NVIDIA GPU's and Apple Silicon will significantly accelerate embedding acceleration (uploading files and documents for Retrieval Augemented Generation "RAG"). NVIDIA GPU's will significantly accelerate embedding acceleration (uploading files and documents for Retrieval Augemented Generation "RAG").
As of release 2.0.34 the minimum GPU VRAM needed at installation time is 4GB as the embedding model installed is teh BAAI/bge-m3 which consumes around 3.78GB once fully loaded onto the GPU. As of release 2.0.34 the minimum GPU VRAM needed at installation time is 4GB as the embedding model installed is teh BAAI/bge-m3 which consumes around 3.78GB once fully loaded onto the GPU.
We will be adjusting the installation scripts in future release so that smaller GPU's down to 1GB can be used on mini desktop computers. We will be adjusting the installation scripts in future release so that smaller GPU's down to 1GB can be used on mini desktop computers.