KeyArgo
/
llama-gpt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add Kubernetes deployment instructions to README.md

This commit is contained in:
Mayank Chhabra 2023-08-18 23:56:43 +07:00 committed by GitHub
parent ca6ec9b370
commit 3553e20a3d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 24 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
README.md
View File

@ -36,11 +36,11 @@ https://github.com/getumbrel/llama-gpt/assets/10330103/5d1a76b8-ed03-4a51-90bd-1
Running LlamaGPT on an [umbrelOS](https://umbrel.com) home server is one click. Simply install it from the [Umbrel App Store](https://apps.umbrel.com/app/llama-gpt). Running LlamaGPT on an [umbrelOS](https://umbrel.com) home server is one click. Simply install it from the [Umbrel App Store](https://apps.umbrel.com/app/llama-gpt).
<!-- Todo: update badge link after launch -->
[![LlamaGPT on Umbrel App Store](https://apps.umbrel.com/app/llama-gpt/badge-light.svg)](https://apps.umbrel.com/app/llama-gpt) [![LlamaGPT on Umbrel App Store](https://apps.umbrel.com/app/llama-gpt/badge-light.svg)](https://apps.umbrel.com/app/llama-gpt)
### Install LlamaGPT anywhere else ---
### Install LlamaGPT anywhere else with Docker
You can run LlamaGPT on any x86 or arm64 system. Make sure you have Docker installed. You can run LlamaGPT on any x86 or arm64 system. Make sure you have Docker installed.
@ -67,6 +67,27 @@ To stop LlamaGPT, run:
docker compose down docker compose down
``` ```
---
### Install LlamaGPT with Kubernetes
First, make sure you have a running Kubernetes cluster and `kubectl` is configured to interact with it.
Then, clone this repo and `cd` into it.
To deploy to Kubernetes first create a namespace:
```bash
kubectl create ns llama
```
Then apply the manifests under the `/deploy/kubernetes` directory with
```bash
kubectl apply -k deploy/kubernetes/. -n llama
```
Expose your service however you would normally do that.
## Benchmarks ## Benchmarks
We've tested LlamaGPT models on the following hardware with the default system prompt, and user prompt: "How does the universe expand?" at temperature 0 to guarantee deterministic results. Generation speed is averaged over the first 10 generations. We've tested LlamaGPT models on the following hardware with the default system prompt, and user prompt: "How does the universe expand?" at temperature 0 to guarantee deterministic results. Generation speed is averaged over the first 10 generations.