-
### Summary
One solution that involves utilizing the Wasmedge runtime's GGML plugin within a container.
### Details
Supports a webassembly application based on the wasi_nn proposal, and the a…
-
With my NVIDIA 1050TI and Ubuntu 23.04 WSL, the model takes a long time to load—about three minutes—but the response is, I believe, faster than with other tools.
Once the first question was answered,…
-
Hello I wish to clear the models knowledge for every loop iteration without tracking previous inputs or outputs. Since the context object is a way to pass information between different parts of the mo…
-
I'm working on the design on FFMpeg plugin on C++ side. I noticed that plugins maintain an internal data structure to hold Structs in c++ ([Example](https://github.com/WasmEdge/WasmEdge/blob/f6d99c87f…
-
rust version: rustc 1.77.1 (7cf61ebde 2024-03-27)
rustup default :stable-x86_64-unknown-linux-gnu (default)
wasmedge version 0.13.5
OS: ubuntu 22.04
After cloning the code from github, I run th…
-
### Summary
I am getting below error while using api-server llama-api-server.wasm both downloading from curl and after building on raspberry-pi5 with raspberrypi-os. It works. well on my mac.
free…
-
Hi, does this support webgpu in the browser?
-
### Is your feature request related to a problem? Please describe.
Readers can find the plugins crate on the plugin page, but it's difficult to locate the documentation on how to use them. Adding a…
-
### Summary
When attempting to run the Llama 2 inference model locally following the instructions at https://wasmedge.org/docs/develop/rust/wasinn/llm_inference, I encountered the following error:
…
-
I'm using Mac M1 hardware. I used the below command to build WasmEdge
```console
$ cmake -DCMAKE_BUILD_TYPE=Release -GNinja -DWASMEDGE_BUILD_AOT_RUNTIME=OFF -DWASMEDGE_PLUGIN_WASI_NN_BACKEND…