Skip to content

Commit

Permalink
Docs cleanup
Browse files Browse the repository at this point in the history
  • Loading branch information
jeremyfowers committed Nov 26, 2024
1 parent 2625b78 commit f50505a
Show file tree
Hide file tree
Showing 2 changed files with 4 additions and 4 deletions.
4 changes: 2 additions & 2 deletions docs/ort_genai_igpu.md
Original file line number Diff line number Diff line change
Expand Up @@ -8,8 +8,8 @@ To install:

1. `conda create -n oga-igpu python=3.9`
1. `conda activate oga-igpu`
1. `pip install -e path/to/genai[oga-igpu]`
- Note: don't forget the `[oga-igpu]` at the end, this is what installs ort-genai
1. `pip install -e .[llm-oga-igpu]`
- Note: don't forget the `[llm-oga-igpu]` at the end, this is what installs ort-genai
1. Get models:
- The oga-load tool can download models from Hugging Face and build ONNX files using oga model_builder. Models can be quantized and optimized for both igpu and cpu.
- Download and build ONNX model files:
Expand Down
4 changes: 2 additions & 2 deletions docs/ort_genai_npu.md
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ onnxruntime-genai (aka OGA) is a new framework created by Microsoft for running
1. `cd REPO_ROOT`
1. `pip install -e .[oga-npu]`
1. Download required OGA packages
1. Access the [AMD RyzenAI EA Lounge](https://account.amd.com/en/member/ryzenai-sw-ea.html#tabs-a5e122f973-item-4757898120-tab) and download `amd_oga_Oct4_2024.zip` from `Ryzen AI 1.3 Preview Release`.
1. Access the [AMD RyzenAI EA Lounge](https://account.amd.com/en/member/ryzenai-sw-ea.html#tabs-a5e122f973-item-4757898120-tab) and download `amd_oga_Oct4_2024.zip` from `Ryzen AI 1.3 EA Release`.
1. Unzip `amd_oga_Oct4_2024.zip`
1. Setup your folder structure:
1. Copy the `amd_oga` folder from the above zip file, if desired
Expand All @@ -35,7 +35,7 @@ onnxruntime-genai (aka OGA) is a new framework created by Microsoft for running

### Runtime

To test basic functionality, point lemonade to any of the models under [quark-quantized-onnx-llms-for-ryzen-ai-13-ea](https://huggingface.co/collections/amd/quark-quantized-onnx-llms-for-ryzen-ai-13-ea-66fc8e24927ec45504381902):
To test basic functionality, point lemonade to any of the models under [quark-quantized-onnx-llms-for-ryzen-ai-1.3-ea](https://huggingface.co/collections/amd/quark-quantized-onnx-llms-for-ryzen-ai-13-ea-66fc8e24927ec45504381902):

```
lemonade -i amd/Llama-2-7b-hf-awq-g128-int4-asym-fp32-onnx-ryzen-strix oga-load --device npu --dtype int4 llm-prompt -p "hello whats your name?" --max-new-tokens 15
Expand Down

0 comments on commit f50505a

Please sign in to comment.