From ca690511612c417a6d2e981618c3a2b9209335aa Mon Sep 17 00:00:00 2001 From: pytorchbot Date: Thu, 11 Apr 2024 17:28:14 -0700 Subject: [PATCH] Add the missing import generate_etrecord to doc Getting Started with LLM (#2977) (#2997) Summary: Pull Request resolved: https://github.com/pytorch/executorch/pull/2977 As titled Reviewed By: Gasoonjia Differential Revision: D55992093 fbshipit-source-id: 7864c330bd86af5d4127cacfd47e96f1e6666bfb (cherry picked from commit cb9caa30ca9c57320bfdc43d33f1d6ad54e56f9f) Co-authored-by: Olivia Liu --- docs/source/llm/getting-started.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/source/llm/getting-started.md b/docs/source/llm/getting-started.md index 3aaa2b2f29..8374374056 100644 --- a/docs/source/llm/getting-started.md +++ b/docs/source/llm/getting-started.md @@ -598,6 +598,7 @@ In your export script, after calling `to_edge()` and `to_executorch()`, call `ge ``` import copy +from executorch.sdk import generate_etrecord # Make the deep copy immediately after to to_edge() edge_manager_copy = copy.deepcopy(edge_manager) @@ -678,7 +679,7 @@ inspector = Inspector(etdump_path="etdump.etdp") with open("inspector_out.txt", "w") as file: inspector.print_data_tabular(file) ``` -This prints the performance data in a tabular format in “inspector_out.txt”, with each row being a profiling event. +This prints the performance data in a tabular format in “inspector_out.txt”, with each row being a profiling event. Top rows look like this: ![](../_static/img/llm_manual_print_data_tabular.png) View in full size