From efeca76cecee945e488d3510966d0a8f79963370 Mon Sep 17 00:00:00 2001 From: Justin Ormont Date: Wed, 14 Jul 2021 15:41:09 -0700 Subject: [PATCH] Update quantization.md (#8351) Spelling fix --- docs/how-to/quantization.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/how-to/quantization.md b/docs/how-to/quantization.md index e55dc48a3f..1715b1d562 100644 --- a/docs/how-to/quantization.md +++ b/docs/how-to/quantization.md @@ -158,7 +158,7 @@ We have 2 E2E examples [Yolo V3](https://github.com/microsoft/onnxruntime/tree/m ### Why am I not seeing performance improvements? {: .no_toc } -Performance improvement depends on your model and hardware. Quantization performance gain comes in 2 part: instruction and cache. Old hardware doesn't have or has few instrction support for byte computation. And quantization has overhead (quantize and dequantize), so it is not rare to get worse performance on old devices. +Performance improvement depends on your model and hardware. Quantization performance gain comes in 2 part: instruction and cache. Old hardware doesn't have or has few instruction support for byte computation. And quantization has overhead (quantize and dequantize), so it is not rare to get worse performance on old devices. x86-64 with VNNI, GPU with Tensor Core int8 support and ARM with dot-product instructions can get better performance in general.