From eb1c331c843cd16ad3c5444fcb0a0ddafc87febe Mon Sep 17 00:00:00 2001
From: Tim Dettmers <tim.dettmers@gmail.com>
Date: Tue, 11 Apr 2023 15:49:01 -0700
Subject: [PATCH] Updates README and CHANGELOG.

---
 CHANGELOG.md           | 8 +++++++-
 README.md              | 2 +-
 compile_from_source.md | 2 +-
 cuda_install.sh        | 2 +-
 deploy.sh              | 4 ++--
 5 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 66578d5..5399c02 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -204,14 +204,20 @@ Improvements:
 
 ### 0.38.0
 
-#### 8-bit Lion, Load/Store 8-bit layers
+#### 8-bit Lion, Load/Store 8-bit Models directly from/to HF Hub
 
 Features:
  - Support for 32 and 8-bit Lion has been added. Thank you @lucidrains
  - Support for serialization of Linear8bitLt layers (LLM.int8()). This allows to store and load 8-bit weights directly from the HuggingFace Hub. Thank you @myrab
+ - New bug report features `python -m bitsandbytes` now gives extensive debugging details to debug CUDA setup failures.
 
 Bug fixes:
  - Fixed a bug where some bitsandbytes methods failed in a model-parallel setup on multiple GPUs. Thank you @tonylins
+ - Fixed a bug where cudart.so libraries could not be found in newer PyTorch releases.
+
+Improvements:
+ - Improved the CUDA Setup procedure by doing a more extensive search for CUDA libraries
 
 Deprecated:
  - Devices with compute capability 3.0 (GTX 700s, K10) and 3.2 (Tegra K1, Jetson TK1) are now deprecated and support will be removed in 0.39.0.
+ - Support for CUDA 10.0 and 10.2 will be removed in bitsandbytes 0.39.0
diff --git a/README.md b/README.md
index 600401c..727a86c 100644
--- a/README.md
+++ b/README.md
@@ -148,7 +148,7 @@ To compile from source, you need an installation of CUDA. If `nvcc` is not insta
 ```bash
 wget https://raw.githubusercontent.com/TimDettmers/bitsandbytes/main/cuda_install.sh
 # Syntax cuda_install CUDA_VERSION INSTALL_PREFIX EXPORT_TO_BASH
-#   CUDA_VERSION in {110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121}
+#   CUDA_VERSION in {110, 111, 112, 113, 114, 115, 116, 117, 118, 120, 121}
 #   EXPORT_TO_BASH in {0, 1} with 0=False and 1=True 
 
 # For example, the following installs CUDA 11.8 to ~/local/cuda-11.8 and exports the path to your .bashrc
diff --git a/compile_from_source.md b/compile_from_source.md
index 7edb33f..9d4f89d 100644
--- a/compile_from_source.md
+++ b/compile_from_source.md
@@ -11,7 +11,7 @@ You can install CUDA locally without sudo by following the following steps:
 ```bash
 wget https://raw.githubusercontent.com/TimDettmers/bitsandbytes/main/cuda_install.sh
 # Syntax cuda_install CUDA_VERSION INSTALL_PREFIX EXPORT_TO_BASH
-#   CUDA_VERSION in {110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121}
+#   CUDA_VERSION in {110, 111, 112, 113, 114, 115, 116, 117, 118, 120, 121}
 #   EXPORT_TO_BASH in {0, 1} with 0=False and 1=True 
 
 # For example, the following installs CUDA 11.7 to ~/local/cuda-11.7 and exports the path to your .bashrc
diff --git a/cuda_install.sh b/cuda_install.sh
index 2e6c7d1..678f7ca 100644
--- a/cuda_install.sh
+++ b/cuda_install.sh
@@ -77,7 +77,7 @@ FILE=$(basename $URL)
 if [[ -n "$CUDA_VERSION" ]]; then
   echo $URL
   echo $FILE
-  wget $URL
+  #wget $URL
   bash $FILE --no-drm --no-man-page --override --toolkitpath=$BASE_PATH/$FOLDER/ --toolkit --silent
   if [ "$EXPORT_BASHRC" -eq "1" ]; then
     echo "export LD_LIBRARY_PATH=\$LD_LIBRARY_PATH:$BASE_PATH/$FOLDER/lib64" >> ~/.bashrc
diff --git a/deploy.sh b/deploy.sh
index 44db970..24d6cbf 100644
--- a/deploy.sh
+++ b/deploy.sh
@@ -10,8 +10,8 @@ if [[ ! -z "${LD_LIBRARY_PATH}" ]]; then
 fi
 
 
-module unload cuda
-module unload gcc
+module unload cuda && echo "no module function available. Probably not on a slurm cluster."
+module unload gcc && echo "no module function available. Probably not on a slurm cluster."
 
 rm -rf dist build
 make cleaneggs