Michael Act
Michael Act
Hi, I have a question regarding environments that are not running on top of HPC (only a single server with GPU). How can I get container name in metrics?
@microsoft-github-policy-service agree
This would be great, it would help isolate EFS usage between PVCs.
Can you PR the changes?
I can confirm when I run with `llama.cpp`, it runs well: ``` services: llama-server: image: ghcr.io/ggml-org/llama.cpp:server ports: - "8000:8000" volumes: - ./models:/models command: - -m - /models/Llama-3.2-3B-Instruct.gguf - --lora -...
Just to confirm, since it’s been about three months, does mem0 history still only support SQLite?
I am also experiencing this issue. I installed the NVIDIA Kubernetes device plugin using the latest Helm chart from https://nvidia.github.io/k8s-device-plugin. Is there anything I should verify? Additionally, I don't see...
Ready for review, thank you!