diff --git a/README.md b/README.md
index 619c6239..8077223a 100644
--- a/README.md
+++ b/README.md
@@ -58,7 +58,7 @@ To define persistent command-line flags like `--listen` or `--api`, edit the `CM
 * There is no need to run any of those scripts as admin/root.
 * For additional instructions about AMD setup, WSL setup, and nvcc installation, consult [this page](https://github.com/oobabooga/text-generation-webui/blob/main/docs/One-Click-Installers.md).
 * The installer has been tested mostly on NVIDIA GPUs. If you can find a way to improve it for your AMD/Intel Arc/Mac Metal GPU, you are highly encouraged to submit a PR to this repository. The main file to be edited is `one_click.py`.
-* For automated installation, you can use the `GPU_CHOICE`, `LAUNCH_AFTER_INSTALL`, and `INSTALL_EXTENSIONS` environment variables. For instance: `GPU_CHOICE=A LAUNCH_AFTER_INSTALL=False INSTALL_EXTENSIONS=False ./start_linux.sh`.
+* For automated installation, you can use the `GPU_CHOICE`, `USE_CUDA118`, `LAUNCH_AFTER_INSTALL`, and `INSTALL_EXTENSIONS` environment variables. For instance: `GPU_CHOICE=A USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE INSTALL_EXTENSIONS=FALSE ./start_linux.sh`.
 
 ### Manual installation using Conda
 
@@ -78,7 +78,7 @@ bash Miniconda3.sh
 #### 1. Create a new conda environment
 
 ```
-conda create -n textgen python=3.10
+conda create -n textgen python=3.11
 conda activate textgen
 ```
 
@@ -86,11 +86,11 @@ conda activate textgen
 
 | System | GPU | Command |
 |--------|---------|---------|
-| Linux/WSL | NVIDIA | `pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118` |
+| Linux/WSL | NVIDIA | `pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121` |
 | Linux/WSL | CPU only | `pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu` |
 | Linux | AMD | `pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm5.6` |
 | MacOS + MPS | Any | `pip3 install torch torchvision torchaudio` |
-| Windows | NVIDIA | `pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118` |
+| Windows | NVIDIA | `pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121` |
 | Windows | CPU only | `pip3 install torch torchvision torchaudio` |
 
 The up-to-date commands can be found here: https://pytorch.org/get-started/locally/.
@@ -98,7 +98,7 @@ The up-to-date commands can be found here: https://pytorch.org/get-started/local
 For NVIDIA, you may also need to manually install the CUDA runtime libraries:
 
 ```
-conda install -y -c "nvidia/label/cuda-11.8.0" cuda-runtime
+conda install -y -c "nvidia/label/cuda-12.1.0" cuda-runtime
 ```
 
 #### 3. Install the web UI
@@ -140,12 +140,18 @@ cd text-generation-webui
 git clone https://github.com/turboderp/exllama repositories/exllama
 ```
 
-##### bitsandbytes on older NVIDIA GPUs
+##### Older NVIDIA GPUs
 
-bitsandbytes >= 0.39 may not work. In that case, to use `--load-in-8bit`, you may have to downgrade like this:
+1) For Kepler GPUs and older, you will need to install CUDA 11.8 instead of 12:
 
-* Linux: `pip install bitsandbytes==0.38.1`
-* Windows: `pip install https://github.com/jllllll/bitsandbytes-windows-webui/raw/main/bitsandbytes-0.38.1-py3-none-any.whl`
+```
+pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+conda install -y -c "nvidia/label/cuda-11.8.0" cuda-runtime
+```
+
+2) bitsandbytes >= 0.39 may not work. In that case, to use `--load-in-8bit`, you may have to downgrade like this:
+    * Linux: `pip install bitsandbytes==0.38.1`
+    * Windows: `pip install https://github.com/jllllll/bitsandbytes-windows-webui/raw/main/bitsandbytes-0.38.1-py3-none-any.whl`
 
 ##### Manual install
 
diff --git a/docker/Dockerfile b/docker/Dockerfile
index 7b14b24f..f0372e54 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -1,4 +1,4 @@
-FROM nvidia/cuda:11.8.0-devel-ubuntu22.04 as builder
+FROM nvidia/cuda:12.1.0-devel-ubuntu22.04 as builder
 
 RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw apt-get update && \
     apt-get install --no-install-recommends -y git vim build-essential python3-dev python3-venv && \
@@ -21,7 +21,7 @@ ARG TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST:-3.5;5.0;6.0;6.1;7.0;7.5;8.0;8.
 RUN . /build/venv/bin/activate && \
     python3 setup_cuda.py bdist_wheel -d .
 
-FROM nvidia/cuda:11.8.0-runtime-ubuntu22.04
+FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04
 
 LABEL maintainer="Your Name <your.email@example.com>"
 LABEL description="Docker image for GPTQ-for-LLaMa and Text Generation WebUI"
diff --git a/modules/exllamav2.py b/modules/exllamav2.py
index 0287a177..558c2365 100644
--- a/modules/exllamav2.py
+++ b/modules/exllamav2.py
@@ -1,4 +1,5 @@
 import random
+import traceback
 from pathlib import Path
 
 import torch
@@ -24,6 +25,9 @@ except ModuleNotFoundError:
         'https://github.com/Dao-AILab/flash-attention#installation-and-features'
     )
     pass
+except Exception:
+    logger.warning('Failed to load flash-attention due to the following error:\n')
+    traceback.print_exc()
 
 
 class Exllamav2Model:
diff --git a/one_click.py b/one_click.py
index ae84cce1..750a126b 100644
--- a/one_click.py
+++ b/one_click.py
@@ -171,8 +171,19 @@ def install_webui():
     install_git = "conda install -y -k ninja git"
     install_pytorch = "python -m pip install torch torchvision torchaudio"
 
+    use_cuda118 = "N"
     if any((is_windows(), is_linux())) and choice == "A":
-        install_pytorch = "python -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118"
+        if "USE_CUDA118" in os.environ:
+            use_cuda118 = os.environ.get("USE_CUDA118", "").lower() in ("yes", "y", "trye", "1", "t", "on")
+        else:
+            # Ask for CUDA version if using NVIDIA
+            print("\nWould you like to use CUDA 11.8 instead of 12.1? This is only necessary for older GPUs like Kepler.\nIf unsure, say \"N\".\n")
+            use_cuda118 = input("Input (Y/N)> ").upper().strip('"\'').strip()
+            while use_cuda118 not in 'YN':
+                print("Invalid choice. Please try again.")
+                use_cuda118 = input("Input> ").upper().strip('"\'').strip()
+
+        install_pytorch = f"python -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/{'cu121' if use_cuda118 == 'N' else 'cu118'}"
     elif not is_macos() and choice == "B":
         if is_linux():
             install_pytorch = "python -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm5.6"
@@ -189,7 +200,7 @@ def install_webui():
 
     # Install CUDA libraries (this wasn't necessary for Pytorch before...)
     if choice == "A":
-        run_cmd("conda install -y -c \"nvidia/label/cuda-11.8.0\" cuda-runtime", assert_success=True, environment=True)
+        run_cmd(f"conda install -y -c \"nvidia/label/{'cuda-12.1.0' if use_cuda118 == 'N' else 'cuda-11.8.0'}\" cuda-runtime", assert_success=True, environment=True)
 
     # Install the webui requirements
     update_requirements(initial_installation=True)
@@ -236,9 +247,11 @@ def update_requirements(initial_installation=False):
     elif initial_installation:
         print_big_message("Will not install extensions due to INSTALL_EXTENSIONS environment variable.")
 
-    # Detect the PyTorch version
+    # Detect the Python and PyTorch versions
     torver = torch_version()
-    is_cuda = '+cu' in torver  # 2.0.1+cu118
+    print(f"TORCH: {torver}")
+    is_cuda = '+cu' in torver
+    is_cuda118 = '+cu118' in torver  # 2.1.0+cu118
     is_cuda117 = '+cu117' in torver  # 2.0.1+cu117
     is_rocm = '+rocm' in torver  # 2.0.1+rocm5.4.2
     is_intel = '+cxx11' in torver  # 2.0.1a0+cxx11.abi
@@ -269,7 +282,9 @@ def update_requirements(initial_installation=False):
     print_big_message(f"Installing webui requirements from file: {requirements_file}")
     textgen_requirements = open(requirements_file).read().splitlines()
     if is_cuda117:
-        textgen_requirements = [req.replace('+cu118', '+cu117').replace('torch2.1', 'torch2.0') for req in textgen_requirements]
+        textgen_requirements = [req.replace('+cu121', '+cu117').replace('torch2.1', 'torch2.0') for req in textgen_requirements]
+    elif is_cuda118:
+        textgen_requirements = [req.replace('+cu121', '+cu118') for req in textgen_requirements]
     with open('temp_requirements.txt', 'w') as file:
         file.write('\n'.join(textgen_requirements))
 
diff --git a/requirements.txt b/requirements.txt
index 8b960aaa..70375c8a 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -37,49 +37,51 @@ https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_
 https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
 
 # CUDA wheels
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-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/v0.0.6/exllamav2-0.0.6+cu118-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/v0.0.6/exllamav2-0.0.6+cu118-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu118torch2.1cxx11abiFALSE-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/v2.3.2/flash_attn-2.3.2+cu118torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu118torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu118torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.27+cu118-py3-none-any.whl
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu121-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/v0.0.6/exllamav2-0.0.6+cu121-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/v0.0.6/exllamav2-0.0.6+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/bdashore3/flash-attention/releases/download/2.3.2-2/flash_attn-2.3.2+cu122-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/bdashore3/flash-attention/releases/download/2.3.2-2/flash_attn-2.3.2+cu122-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-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/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.27+cu121-py3-none-any.whl
 autoawq==0.1.4
diff --git a/requirements_noavx2.txt b/requirements_noavx2.txt
index 6f0b7dc3..3bb5bc90 100644
--- a/requirements_noavx2.txt
+++ b/requirements_noavx2.txt
@@ -37,49 +37,51 @@ https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/
 https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
 
 # CUDA wheels
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-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/v0.0.6/exllamav2-0.0.6+cu118-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/v0.0.6/exllamav2-0.0.6+cu118-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu118torch2.1cxx11abiFALSE-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/v2.3.2/flash_attn-2.3.2+cu118torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu118torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu118torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118avx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118avx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118avx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu118avx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu118-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX/ctransformers-0.2.27+cu118-py3-none-any.whl
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu121-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/v0.0.6/exllamav2-0.0.6+cu121-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/v0.0.6/exllamav2-0.0.6+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/bdashore3/flash-attention/releases/download/2.3.2-2/flash_attn-2.3.2+cu122-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/bdashore3/flash-attention/releases/download/2.3.2-2/flash_attn-2.3.2+cu122-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-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/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX/ctransformers-0.2.27+cu121-py3-none-any.whl
 autoawq==0.1.4
diff --git a/start_linux.sh b/start_linux.sh
index d9d2ab07..948e40b8 100755
--- a/start_linux.sh
+++ b/start_linux.sh
@@ -43,7 +43,7 @@ fi
 
 # create the installer env
 if [ ! -e "$INSTALL_ENV_DIR" ]; then
-    "$CONDA_ROOT_PREFIX/bin/conda" create -y -k --prefix "$INSTALL_ENV_DIR" python=3.10
+    "$CONDA_ROOT_PREFIX/bin/conda" create -y -k --prefix "$INSTALL_ENV_DIR" python=3.11
 fi
 
 # check if conda environment was actually created
diff --git a/start_macos.sh b/start_macos.sh
index 7fa82d81..5877e167 100755
--- a/start_macos.sh
+++ b/start_macos.sh
@@ -43,7 +43,7 @@ fi
 
 # create the installer env
 if [ ! -e "$INSTALL_ENV_DIR" ]; then
-    "$CONDA_ROOT_PREFIX/bin/conda" create -y -k --prefix "$INSTALL_ENV_DIR" python=3.10
+    "$CONDA_ROOT_PREFIX/bin/conda" create -y -k --prefix "$INSTALL_ENV_DIR" python=3.11
 fi
 
 # check if conda environment was actually created
diff --git a/start_windows.bat b/start_windows.bat
index 4e6f6fe7..cdc303e4 100755
--- a/start_windows.bat
+++ b/start_windows.bat
@@ -50,7 +50,7 @@ if "%conda_exists%" == "F" (
 @rem create the installer env
 if not exist "%INSTALL_ENV_DIR%" (
 	echo Packages to install: %PACKAGES_TO_INSTALL%
-	call "%CONDA_ROOT_PREFIX%\_conda.exe" create --no-shortcuts -y -k --prefix "%INSTALL_ENV_DIR%" python=3.10 || ( echo. && echo Conda environment creation failed. && goto end )
+	call "%CONDA_ROOT_PREFIX%\_conda.exe" create --no-shortcuts -y -k --prefix "%INSTALL_ENV_DIR%" python=3.11 || ( echo. && echo Conda environment creation failed. && goto end )
 )
 
 @rem check if conda environment was actually created
diff --git a/wsl.sh b/wsl.sh
index 32ee585d..5c7d6212 100755
--- a/wsl.sh
+++ b/wsl.sh
@@ -70,7 +70,7 @@ fi
 
 # create the installer env
 if [ ! -e "$INSTALL_ENV_DIR" ]; then
-    "$CONDA_ROOT_PREFIX/bin/conda" create -y -k --prefix "$INSTALL_ENV_DIR" python=3.10 git
+    "$CONDA_ROOT_PREFIX/bin/conda" create -y -k --prefix "$INSTALL_ENV_DIR" python=3.11 git
 fi
 
 # check if conda environment was actually created