From fa2a2986ff225d26b45d2e7522631926feed2625 Mon Sep 17 00:00:00 2001 From: Albert Catalan Tatjer Date: Wed, 14 Aug 2024 16:42:47 +0200 Subject: [PATCH] Fix typos in quantization.mdx (#1989) Fix typos quantization.mdx Fixed 3 typos --- docs/source/concept_guides/quantization.mdx | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/source/concept_guides/quantization.mdx b/docs/source/concept_guides/quantization.mdx index 5580a13e2ad..386a7afbf05 100644 --- a/docs/source/concept_guides/quantization.mdx +++ b/docs/source/concept_guides/quantization.mdx @@ -95,11 +95,11 @@ paragraph. ### Symmetric and affine quantization schemes -The equation above is called the *affine quantization sheme* because the mapping from `[a, b]` to `int8` is an affine one. +The equation above is called the *affine quantization scheme* because the mapping from `[a, b]` to `int8` is an affine one. A common special case of this scheme is the *symmetric quantization scheme*, where we consider a symmetric range of float values `[-a, a]`. -In this case the integer space is usally `[-127, 127]`, meaning that the `-128` is opted out of the regular `[-128, 127]` signed `int8` range. -The reason being that having both ranges symmetric allows to have `Z = 0`. While one value out of the 256 representable +In this case the integer space is usually `[-127, 127]`, meaning that the `-128` is opted out of the regular `[-128, 127]` signed `int8` range. +The reason being that having a symmetric range allows to have `Z = 0`. While one value out of the 256 representable values is lost, it can provide a speedup since a lot of addition operations can be skipped. **Note**: To learn how the quantization parameters `S` and `Z` are computed, you can read the