huggingface / huggingface/optimum-amd
[RyzenAI] Packaging and documentation of RyzenAI-SW
- Dominant language
- Jupyter Notebook
- Stars
- 101
- Forks
- 21
- Avg merge
- 58m
- Merged PRs (30d)
- 1
Description
User experience for running OPT-like models using VitisEP:
* Currently, the user needs to download the `RyzenAI-SW` repository and set environment variables. It could be better to provide the [DLLs ](https://github.com/amd/RyzenAI-SW/tree/main/example/transformers/dll)and required packages (ex. [thirdparty](https://github.com/amd/RyzenAI-SW/tree/main/example/transformers/third_party) etc) within the SDK itself or make them available through PyPI?
* Detailed documentation available on the environment variables set in the examples, as well as guidelines on which scenarios require which settings? For instance: `set DEVICE=phx set TVM_GEMM_M=1,8 set TVM_DLL_NUM=2`
* Detailed documentation for the builtin params used in the examples ( ex impl and quant_mode)
* Documentation of `vaip_config.json`
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.