Create placeholder pages for LLM TOC. (#2419)

Summary: Pull Request resolved: #2419

Differential Revision: D54878408

Author: Xingying Cheng

docs/source/index.rst

@@ -79,6 +79,17 @@ Topics in this section will help you get started with ExecuTorch.
    getting-started-setup
    runtime-build-and-cross-compilation
 
+.. toctree::
+   :glob:
+   :maxdepth: 1
+   :caption: LLM
+   :hidden:
+
+   llm-introduction
+   llm-on-mobile
+   llm-on-desktop
+   llm-on-advanced-flow
+
 .. toctree::
    :glob:
    :maxdepth: 1

docs/source/llm-advanced-flow.md

@@ -0,0 +1,7 @@
+# Advanced Flows
+
+## Custom quantization
+
+## Bring GGUF to PyTorch ecosystem
+
+## TorchTune interoperability

docs/source/llm-introduction.md

@@ -0,0 +1,5 @@
+# LLM Introduction
+
+[Current landscape of local LLMs]
+[What is our offering?]
+[Why and when should you use it?]

docs/source/llm-on-desktop.md

@@ -0,0 +1,7 @@
+# Enabling LLMs on Desktop
+
+## Local Llama on Desktop Benchmarks
+
+**Results**
+
+**Instructions**

docs/source/llm-on-mobile.md

@@ -0,0 +1,40 @@
+# Enabling LLMs on Mobile
+
+
+## Local Llama on Mobile Benchmarks
+
+**Results**
+
+**Instructions**
+
+
+
+## Getting Started with LLMs via ExecuTorch
+
+**Simple “Hello World” example**
+
+**Use Mobile Acceleration**
+
+**Quantization via XNNPACKQuantizer**
+
+**Debugging and Profiling**
+
+**Build Mobile LLM chat App Examples**
+
+
+
+## Customization examples:
+
+**Custom tokenization**
+
+**Custom sampler**
+
+**Speculative decoding**
+
+**Modify a mobile app to use a different LLM model**
+
+
+
+## Validating other models
+
+**Exportability results**

install_requirements.sh

@@ -49,4 +49,5 @@ pip install --pre torchsr==${TORCHSR_VERSION}
 pip install . --no-build-isolation
 
 # Install flatc dependency
-bash build/install_flatc.sh
+# bash build/install_flatc.sh
+bash install_flatc.sh