From f1b67dfd14bd7bd9560ed99799757cc363432b56 Mon Sep 17 00:00:00 2001 From: roublardise <> Date: Thu, 27 Mar 2025 15:32:00 +0100 Subject: [PATCH] chore: fix documentation typos --- docs/Installation.md | 2 +- docs/PythonAPI.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/Installation.md b/docs/Installation.md index a50d478ef..ab341c4f7 100644 --- a/docs/Installation.md +++ b/docs/Installation.md @@ -7,7 +7,7 @@ - **Python Version**: >= 3.8 - **CUDA Version**: >= 11.0 -The easiest way to install BitBLAS is direcly from the PyPi using pip. To install the latest version, run the following command in your terminal. +The easiest way to install BitBLAS is directly from the PyPi using pip. To install the latest version, run the following command in your terminal. **Note**: Currently, BitBLAS whl is only supported on Ubuntu 20.04 or later version as we build the whl files on this platform. Currently we only provide whl files for CUDA>=11.0 and with Python>=3.8. **If you are using a different platform or environment, you may need to [build BitBLAS from source](https://github.com/microsoft/BitBLAS/blob/main/docs/Installation.md#building-from-source).** diff --git a/docs/PythonAPI.md b/docs/PythonAPI.md index 45f23df2b..1e248671f 100644 --- a/docs/PythonAPI.md +++ b/docs/PythonAPI.md @@ -184,7 +184,7 @@ Returns: The output tensor. #### `init_params()` -Initializes parameters handles (convert constant params into ctypes void pointer) for the computation. We currently put this fuction in the forward function, so you do not need to call it manually. But if you lift this function out of the forward function, you can call it manually to aoid the transformation. +Initializes parameters handles (convert constant params into ctypes void pointer) for the computation. We currently put this function in the forward function, so you do not need to call it manually. But if you lift this function out of the forward function, you can call it manually to aoid the transformation. #### `load_and_transform_weight(weight, scales=None, zeros=None, bias=None)`