From 5a686cf77edba59e1a4f6612068fa079caf28e72 Mon Sep 17 00:00:00 2001
From: Kimish Patel <kimishpatel@fb.com>
Date: Wed, 9 Apr 2025 20:22:02 -0700
Subject: [PATCH] [pytorch/executorch][diff_train] Fix LLM getting-started.md
 (#10028)

Remove unnecessary line
Fix ETDump part


Internal:
<< DO NOT EDIT BELOW THIS LINE >>

**GitHub Author**: Hansong <107070759+kirklandsign@users.noreply.github.com> (Meta Employee)
**GitHub Repo**: [pytorch/executorch](https://github.com/pytorch/executorch)
**GitHub Pull Request**: [#10028](https://github.com/pytorch/executorch/pull/10028)

Initially generated by: https://www.internalfb.com/intern/sandcastle/job/31525199173943941/

This was imported as part of a Diff Train.
Please review this as soon as possible. Since it is a direct copy of a commit on
GitHub, there shouldn't be much to do.

diff-train-source-id: 7e8eb2b0e688f55c830ca0cf370440ab987e3bdc

Differential Revision: [D72765239](https://our.internmc.facebook.com/intern/diff/D72765239/)

[ghstack-poisoned]
---
 docs/source/llm/getting-started.md | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/docs/source/llm/getting-started.md b/docs/source/llm/getting-started.md
index 035da31f119..f19982660ae 100644
--- a/docs/source/llm/getting-started.md
+++ b/docs/source/llm/getting-started.md
@@ -395,7 +395,6 @@ At this point, the working directory should contain the following files:
 
 If all of these are present, you can now build and run:
 ```bash
-./install_executorch.sh --clean
 (mkdir cmake-out && cd cmake-out && cmake ..)
 cmake --build cmake-out -j10
 ./cmake-out/nanogpt_runner
@@ -661,19 +660,15 @@ edge_config = get_xnnpack_edge_compile_config()
 # Convert to edge dialect and lower to XNNPack.
 edge_manager = to_edge_transform_and_lower(traced_model, partitioner = [XnnpackPartitioner()], compile_config = edge_config)
 et_program = edge_manager.to_executorch()
-```
-
-Finally, ensure that the runner links against the `xnnpack_backend` target in CMakeLists.txt.
 
+with open("nanogpt.pte", "wb") as file:
+    file.write(et_program.buffer)
 ```
-add_executable(nanogpt_runner main.cpp)
-target_link_libraries(
-    nanogpt_runner
-    PRIVATE
-    executorch
-    extension_module_static # Provides the Module class
-    optimized_native_cpu_ops_lib # Provides baseline cross-platform kernels
-    xnnpack_backend) # Provides the XNNPACK CPU acceleration backend
+
+Then run:
+```bash
+python export_nanogpt.py
+./cmake-out/nanogpt_runner
 ```
 
 For more information, see [Quantization in ExecuTorch](../quantization-overview.md).
@@ -782,11 +777,14 @@ Run the export script and the ETRecord will be generated as `etrecord.bin`.
 
 An ETDump is an artifact generated at runtime containing a trace of the model execution. For more information, see [the ETDump docs](../etdump.md).
 
-Include the ETDump header in your code.
+Include the ETDump header and namespace in your code.
 ```cpp
 // main.cpp
 
 #include <executorch/devtools/etdump/etdump_flatcc.h>
+
+using executorch::etdump::ETDumpGen;
+using torch::executor::etdump_result;
 ```
 
 Create an Instance of the ETDumpGen class and pass it to the Module constructor.