From 8930bfc5f487b78fe103a1b66bd81fc9d7a84a1d Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Thu, 13 Jun 2024 20:38:31 -0300
Subject: [PATCH] Bump PyTorch, ExLlamaV2, flash-attention (#6122)

---
 README.md                      | 14 +++++++-------
 one_click.py                   |  6 +++---
 requirements.txt               | 18 +++++++++---------
 requirements_amd.txt           |  6 +++---
 requirements_amd_noavx2.txt    |  6 +++---
 requirements_apple_intel.txt   |  2 +-
 requirements_apple_silicon.txt |  2 +-
 requirements_noavx2.txt        | 18 +++++++++---------
 8 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/README.md b/README.md
index a699a9ab..9655ea79 100644
--- a/README.md
+++ b/README.md
@@ -76,12 +76,12 @@ conda activate textgen
 
 | System | GPU | Command |
 |--------|---------|---------|
-| Linux/WSL | NVIDIA | `pip3 install torch==2.2.1 torchvision==0.17.1 torchaudio==2.2.1 --index-url https://download.pytorch.org/whl/cu121` |
-| Linux/WSL | CPU only | `pip3 install torch==2.2.1 torchvision==0.17.1 torchaudio==2.2.1 --index-url https://download.pytorch.org/whl/cpu` |
-| Linux | AMD | `pip3 install torch==2.2.1 torchvision==0.17.1 torchaudio==2.2.1 --index-url https://download.pytorch.org/whl/rocm5.6` |
-| MacOS + MPS | Any | `pip3 install torch==2.2.1 torchvision==0.17.1 torchaudio==2.2.1` |
-| Windows | NVIDIA | `pip3 install torch==2.2.1 torchvision==0.17.1 torchaudio==2.2.1 --index-url https://download.pytorch.org/whl/cu121` |
-| Windows | CPU only | `pip3 install torch==2.2.1 torchvision==0.17.1 torchaudio==2.2.1` |
+| Linux/WSL | NVIDIA | `pip3 install torch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 --index-url https://download.pytorch.org/whl/cu121` |
+| Linux/WSL | CPU only | `pip3 install torch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 --index-url https://download.pytorch.org/whl/cpu` |
+| Linux | AMD | `pip3 install torch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 --index-url https://download.pytorch.org/whl/rocm5.6` |
+| MacOS + MPS | Any | `pip3 install torch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1` |
+| Windows | NVIDIA | `pip3 install torch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 --index-url https://download.pytorch.org/whl/cu121` |
+| Windows | CPU only | `pip3 install torch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1` |
 
 The up-to-date commands can be found here: https://pytorch.org/get-started/locally/.
 
@@ -146,7 +146,7 @@ Then browse to
 1) For Kepler GPUs and older, you will need to install CUDA 11.8 instead of 12:
 
 ```
-pip3 install torch==2.2.1 torchvision==0.17.1 torchaudio==2.2.1 --index-url https://download.pytorch.org/whl/cu118
+pip3 install torch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 --index-url https://download.pytorch.org/whl/cu118
 conda install -y -c "nvidia/label/cuda-11.8.0" cuda-runtime
 ```
 
diff --git a/one_click.py b/one_click.py
index 55a4a3db..187b3c89 100644
--- a/one_click.py
+++ b/one_click.py
@@ -16,9 +16,9 @@ import sys
 
 
 # Define the required PyTorch version
-TORCH_VERSION = "2.2.1"
-TORCHVISION_VERSION = "0.17.1"
-TORCHAUDIO_VERSION = "2.2.1"
+TORCH_VERSION = "2.3.1"
+TORCHVISION_VERSION = "0.18.1"
+TORCHAUDIO_VERSION = "2.3.1"
 
 # Environment
 script_dir = os.getcwd()
diff --git a/requirements.txt b/requirements.txt
index c1c63504..012df8d2 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -53,13 +53,13 @@ https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/te
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.75+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 
 # CUDA wheels
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
-https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5+cu121.torch2.3.1-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5+cu121.torch2.3.1-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5+cu121.torch2.3.1-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5+cu121.torch2.3.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
+https://github.com/oobabooga/flash-attention/releases/download/v2.5.9.post1/flash_attn-2.5.9.post1+cu122torch2.3.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/flash-attention/releases/download/v2.5.9.post1/flash_attn-2.5.9.post1+cu122torch2.3.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.9.post1/flash_attn-2.5.9.post1+cu122torch2.3cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.9.post1/flash_attn-2.5.9.post1+cu122torch2.3cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 autoawq==0.2.5; platform_system == "Linux" or platform_system == "Windows"
diff --git a/requirements_amd.txt b/requirements_amd.txt
index 8489a97c..01c50dd7 100644
--- a/requirements_amd.txt
+++ b/requirements_amd.txt
@@ -40,8 +40,8 @@ https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cp
 # AMD wheels
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.75+rocm5.6.1-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.75+rocm5.6.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5+rocm5.6.torch2.2.2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5+rocm5.6.torch2.2.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
 https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.5/autoawq-0.2.5+rocm561-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.5/autoawq-0.2.5+rocm561-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
diff --git a/requirements_amd_noavx2.txt b/requirements_amd_noavx2.txt
index 68a82f40..937fdbae 100644
--- a/requirements_amd_noavx2.txt
+++ b/requirements_amd_noavx2.txt
@@ -38,8 +38,8 @@ https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cp
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
 
 # AMD wheels
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5+rocm5.6.torch2.2.2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5+rocm5.6.torch2.2.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
 https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.5/autoawq-0.2.5+rocm561-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.5/autoawq-0.2.5+rocm561-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
diff --git a/requirements_apple_intel.txt b/requirements_apple_intel.txt
index d3cecd08..75973459 100644
--- a/requirements_apple_intel.txt
+++ b/requirements_apple_intel.txt
@@ -38,4 +38,4 @@ https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/me
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp310-cp310-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10"
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp311-cp311-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp310-cp310-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20-py3-none-any.whl
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5-py3-none-any.whl
diff --git a/requirements_apple_silicon.txt b/requirements_apple_silicon.txt
index c940cc52..542ab52f 100644
--- a/requirements_apple_silicon.txt
+++ b/requirements_apple_silicon.txt
@@ -40,4 +40,4 @@ https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/me
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp310-cp310-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.10"
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp311-cp311-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp310-cp310-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20-py3-none-any.whl
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5-py3-none-any.whl
diff --git a/requirements_noavx2.txt b/requirements_noavx2.txt
index c110be62..376ba0fd 100644
--- a/requirements_noavx2.txt
+++ b/requirements_noavx2.txt
@@ -53,13 +53,13 @@ https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/te
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.75+cu121avx-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 
 # CUDA wheels
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
-https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5+cu121.torch2.3.1-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5+cu121.torch2.3.1-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5+cu121.torch2.3.1-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5+cu121.torch2.3.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.1.5/exllamav2-0.1.5-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
+https://github.com/oobabooga/flash-attention/releases/download/v2.5.9.post1/flash_attn-2.5.9.post1+cu122torch2.3.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/flash-attention/releases/download/v2.5.9.post1/flash_attn-2.5.9.post1+cu122torch2.3.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.9.post1/flash_attn-2.5.9.post1+cu122torch2.3cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.9.post1/flash_attn-2.5.9.post1+cu122torch2.3cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 autoawq==0.2.5; platform_system == "Linux" or platform_system == "Windows"