From 30367f5eb1d4f148e90074dcaa2717a720b987f1 Mon Sep 17 00:00:00 2001
From: "Pingchuan Ma (Henry)" <58333343+HensonMa@users.noreply.github.com>
Date: Sat, 6 May 2023 22:15:42 +0800
Subject: [PATCH] [Nano] Add how-to-guide for pytorch async pipeline (#8146)

* add how-to-guide for pytorch async pipeline

* revise introduction

* resolve image issues
---
 docs/readthedocs/source/_toc.yml                               | 1 +
 .../PyTorch/accelerate_pytorch_inference_async_pipeline.nblink | 3 +++
 .../source/doc/Nano/Howto/Inference/PyTorch/index.rst          | 3 ++-
 docs/readthedocs/source/doc/Nano/Howto/index.rst               | 1 +
 4 files changed, 7 insertions(+), 1 deletion(-)
 create mode 100644 docs/readthedocs/source/doc/Nano/Howto/Inference/PyTorch/accelerate_pytorch_inference_async_pipeline.nblink

diff --git a/docs/readthedocs/source/_toc.yml b/docs/readthedocs/source/_toc.yml
index d4763c59..268afb4f 100644
--- a/docs/readthedocs/source/_toc.yml
+++ b/docs/readthedocs/source/_toc.yml
@@ -170,6 +170,7 @@ subtrees:
                               - file: doc/Nano/Howto/Inference/PyTorch/pytorch_save_and_load_openvino
                               - file: doc/Nano/Howto/Inference/PyTorch/multi_instance_pytorch_inference
                               - file: doc/Nano/Howto/Inference/PyTorch/accelerate_pytorch_inference_gpu
+                              - file: doc/Nano/Howto/Inference/PyTorch/accelerate_pytorch_inference_async_pipeline
                         - file: doc/Nano/Howto/Inference/TensorFlow/index
                           title: "TensorFlow"
                           subtrees:
diff --git a/docs/readthedocs/source/doc/Nano/Howto/Inference/PyTorch/accelerate_pytorch_inference_async_pipeline.nblink b/docs/readthedocs/source/doc/Nano/Howto/Inference/PyTorch/accelerate_pytorch_inference_async_pipeline.nblink
new file mode 100644
index 00000000..4dd6ac54
--- /dev/null
+++ b/docs/readthedocs/source/doc/Nano/Howto/Inference/PyTorch/accelerate_pytorch_inference_async_pipeline.nblink
@@ -0,0 +1,3 @@
+{
+    "path": "../../../../../../../../python/nano/tutorial/notebook/inference/pytorch/accelerate_pytorch_inference_async_pipeline.ipynb"
+}
\ No newline at end of file
diff --git a/docs/readthedocs/source/doc/Nano/Howto/Inference/PyTorch/index.rst b/docs/readthedocs/source/doc/Nano/Howto/Inference/PyTorch/index.rst
index fbe4362e..3de72aa1 100644
--- a/docs/readthedocs/source/doc/Nano/Howto/Inference/PyTorch/index.rst
+++ b/docs/readthedocs/source/doc/Nano/Howto/Inference/PyTorch/index.rst
@@ -13,4 +13,5 @@ Inference Optimization: For PyTorch Users
 * `How to save and load optimized JIT model <pytorch_save_and_load_jit.html>`_
 * `How to save and load optimized IPEX model <pytorch_save_and_load_ipex.html>`_
 * `How to accelerate a PyTorch inference pipeline through multiple instances <multi_instance_pytorch_inference.html>`_
-* `How to accelerate a PyTorch inference pipeline using Intel ARC series dGPU <accelerate_pytorch_inference_gpu.html>`_
\ No newline at end of file
+* `How to accelerate a PyTorch inference pipeline using Intel ARC series dGPU <accelerate_pytorch_inference_gpu.html>`_
+* `How to accelerate PyTorch inference using async multi-stage pipeline <accelerate_pytorch_inference_async_pipeline.html>`_
\ No newline at end of file
diff --git a/docs/readthedocs/source/doc/Nano/Howto/index.rst b/docs/readthedocs/source/doc/Nano/Howto/index.rst
index 8b83e951..a33f128e 100644
--- a/docs/readthedocs/source/doc/Nano/Howto/index.rst
+++ b/docs/readthedocs/source/doc/Nano/Howto/index.rst
@@ -77,6 +77,7 @@ PyTorch
 * `How to save and load optimized IPEX model <Inference/PyTorch/pytorch_save_and_load_ipex.html>`_
 * `How to accelerate a PyTorch inference pipeline through multiple instances <Inference/PyTorch/multi_instance_pytorch_inference.html>`_
 * `How to accelerate a PyTorch inference pipeline using Intel ARC series dGPU <Inference/PyTorch/accelerate_pytorch_inference_gpu.html>`_
+* `How to accelerate PyTorch inference using async multi-stage pipeline <Inference/PyTorch/accelerate_pytorch_inference_async_pipeline.html>`_
 
 TensorFlow
 ~~~~~~~~~~~~~~~~~~~~~~~~~