huggingface / huggingface/optimum-amd

[RyzenAI] Packaging and documentation of RyzenAI-SW

Open
#125 0 comments 0 reactions 0 assignees View on GitHub
documentation Ryzen AI
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.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.