From 8dd777495f7845959be8b8819a421868917b8bc0 Mon Sep 17 00:00:00 2001 From: pytorchbot Date: Wed, 16 Oct 2024 19:50:41 -0700 Subject: [PATCH] Update landing page to include Llama (#6218) (#6259) * Update landing page to include Llama (#6231) Summary: Pull Request resolved: https://github.com/pytorch/executorch/pull/6231 We should promote llama page more and demote the LLM Manual. allow-large-files bypass-github-export-checks bypass-github-pytorch-ci-checks bypass-github-executorch-ci-checks Reviewed By: dvorjackz Differential Revision: D64375318 fbshipit-source-id: a6b07de4735691b5230e51ec7bc1957ce9a4463f (cherry picked from commit 3e052a8908c2223020fb997d3ea79af85c948268) * Update index.rst * Update getting-started.md --------- Co-authored-by: Mergen Nachin --- docs/source/index.rst | 16 ++++++++-------- docs/source/llm/getting-started.md | 4 +++- docs/source/llm/llama.md | 5 +++++ 3 files changed, 16 insertions(+), 9 deletions(-) create mode 100644 docs/source/llm/llama.md diff --git a/docs/source/index.rst b/docs/source/index.rst index b8c72f8ee2..4386bf3840 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -60,13 +60,12 @@ Topics in this section will help you get started with ExecuTorch. ExecuTorch. .. grid-item-card:: :octicon:`file-code;1em` - ExecuTorch Intermediate Representation API + ExecuTorch Llama :img-top: _static/img/card-background.svg - :link: ir-exir.html + :link: llm/llama.html :link-type: url - Learn about EXIR, a graph-based intermediate - representation (IR) of PyTorch programs. + Learn about running Llama models via ExecuTorch .. toctree:: :glob: @@ -122,10 +121,11 @@ Topics in this section will help you get started with ExecuTorch. :caption: Working with LLMs :hidden: - llm/getting-started - llm/llama-demo-android - llm/build-run-llama3-qualcomm-ai-engine-direct-backend - llm/llama-demo-ios + Llama + Llama on Android + Llama on iOS + Llama on Android via Qualcomm backend + Intro to LLMs in ExecuTorch .. toctree:: :glob: diff --git a/docs/source/llm/getting-started.md b/docs/source/llm/getting-started.md index cca62edaf8..05a3639e1b 100644 --- a/docs/source/llm/getting-started.md +++ b/docs/source/llm/getting-started.md @@ -1,4 +1,4 @@ -# Getting Started with LLMs via ExecuTorch +# Intro to LLMs in ExecuTorch Welcome to LLM Manual! This manual is designed to provide a practical example to leverage ExecuTorch in onboarding your own Large Language Models (LLMs). Our primary goal is to offer @@ -13,6 +13,8 @@ We encourage users to use this project as a starting point and adapt it to their which includes creating your own versions of the tokenizer, sampler, acceleration backends, and other components. We hope this project serves as a useful guide in your journey with LLMs and ExecuTorch. +For deploying Llama with optimal performance, please see [Llama guide](./llama.md). + ### Table Of Contents diff --git a/docs/source/llm/llama.md b/docs/source/llm/llama.md new file mode 100644 index 0000000000..2d266ba7ae --- /dev/null +++ b/docs/source/llm/llama.md @@ -0,0 +1,5 @@ +# Llama on ExecuTorch + +See +[Llama readme](https://github.com/pytorch/executorch/blob/main/examples/models/llama2/README.md) +for detailed information about running Llama on ExecuTorch.