dm4
dm4
> is this issue open for contributions? if yes I would love to look into this. Yes, this issue is open for contributions. We welcome your input and any code...
I believe we should implement the `LoadByNameWithConfig` function in the NNRPC component. However, before proceeding with its implementation, I can provide a new example that does not utilize the `LoadByNameWithConfig`...
I have added a new example, [wasmedge-ggml/nnrpc](https://github.com/second-state/WasmEdge-WASINN-examples/tree/master/wasmedge-ggml/nnrpc), which avoids using `load_by_name_with_config` to ensure the current version of `wasi_nn_rpcserver` works properly. Additionally, in #3296, I implemented the `LoadByNameWithConfig` function in the...
PR #3296 is merge. This issue should be fixed after the next release.
Then we could extend the list of backends with their corresponding indexes: - 0: Openvino - 1: Onnx - 2: Tensorflow - 3: Pytorch - 4: TensorflowLite - 5: Autodetect...
Okay, we will use `12` for ChatTTS.
It looks like we'll use index 13 for the OpenVINO GenAI backend: https://github.com/WasmEdge/WasmEdge/pull/4034.
Theme: Proposal Description: WASI-NN GGML plugin with latest llama.cpp integration Timeline: Q3 / 2024 Assignee: Me
I have some thoughts: 1. It looks like the implementation of the piper backend directly puts the json format config into `Builders[0]` and passes it into `load()`. I wonder if...
> > 1. It looks like the implementation of the piper backend directly puts the json format config into `Builders[0]` and passes it into `load()`. I wonder if using this...