Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

doc: Update llamaedge app docs #164

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

doc: Update llamaedge app docs #164

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 13 additions & 2 deletions docs/wasm/How-to-run-Llama-3-8B-with-Kubernetes.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ details in: https://www.secondstate.io/articles/wasm-runtime-agi/.

## How to run a llm inference application in Kuasar?

Since Kuasar v0.8.0, Kuasar wasm-sandboxer with `wasmedge` and `wasmedge_wasi_nn`
Since Kuasar v1.0.0, Kuasar wasm-sandboxer with `wasmedge` and `wasmedge_wasi_nn`
features allows your WasmEdge application use the ability of WASI API for
performing Machine Learning inference: https://github.com/WebAssembly/wasi-nn.

Expand All @@ -22,7 +22,6 @@ which introducing how to create an OpenAI-compatible API service for Llama-3-8B.
+ Install WasmEdge and plugins:
`curl -sSf https://raw.githubusercontent.com/WasmEdge/WasmEdge/master/utils/install.sh | bash -s -- -v 0.13.5 --plugins wasi_logging wasi_nn-ggml`


### 1. Build docker image

We already have an example docker image on dockerhub: `docker.io/kuasario/llama-api-server:v1`.
Expand Down Expand Up @@ -50,6 +49,18 @@ CMD ["llama-api-server.wasm", "--prompt-template", "llama-3-chat", "--ctx-size",
```
Build it with `docker build -t docker.io/kuasario/llama-api-server:v1 .`

Otherwise, you can use this DOCKERFILE if you are debugging while developing:
```dockerfile
FROM ubuntu:22.04
RUN apt-get update && apt-get install -y curl
RUN curl -LO https://huggingface.co/second-state/Llama-3-8B-Instruct-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-Q5_K_M.gguf
RUN curl -LO https://github.com/second-state/chatbot-ui/releases/latest/download/chatbot-ui.tar.gz; tar xzf chatbot-ui.tar.gz; rm chatbot-ui.tar.gz
COPY *.wasm .
```

This would download all prerequisites to docker image cache, allowing you pay attention only on development.
`docker build -f Dockerfile -t docker.io/kuasario/llama-api-server:v2 $path_to_app`

### 2. Build and run Kuasar Wasm Sandboxer

```bash
Expand Down
Loading