From 15bb22790eb6cd28dbd62ab1723f1d170ad052fb Mon Sep 17 00:00:00 2001
From: leslie-fang-intel <leslie.fang@intel.com>
Date: Tue, 24 Oct 2023 09:18:42 +0800
Subject: [PATCH] Add x86InductorQuantizer Performance Number

---
 prototype_source/pt2e_quant_ptq_x86_inductor.rst | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/prototype_source/pt2e_quant_ptq_x86_inductor.rst b/prototype_source/pt2e_quant_ptq_x86_inductor.rst
index 915148be81e..1a6e152c996 100644
--- a/prototype_source/pt2e_quant_ptq_x86_inductor.rst
+++ b/prototype_source/pt2e_quant_ptq_x86_inductor.rst
@@ -180,6 +180,10 @@ For example:
 
     TORCHINDUCTOR_FREEZING=1 python example_x86inductorquantizer_pytorch_2_1.py
 
+With PyTorch 2.1 release, all CNN models from TorchBench test suite have been measured and proven effective comparing with Inductor FP32 inference path. Please refer
+to `this document <https://dev-discuss.pytorch.org/t/torchinductor-update-6-cpu-backend-performance-update-and-new-features-in-pytorch-2-1/1514#int8-inference-with-post-training-static-quantization-3>`_
+for detail benchmark number.
+
 4. Conclusion
 ---------------