diff --git a/modules/llamacpp_hf.py b/modules/llamacpp_hf.py
index ff0e8267..366fdf85 100644
--- a/modules/llamacpp_hf.py
+++ b/modules/llamacpp_hf.py
@@ -198,7 +198,6 @@ class LlamacppHF(PreTrainedModel):
             'use_mmap': not shared.args.no_mmap,
             'use_mlock': shared.args.mlock,
             'mul_mat_q': shared.args.mul_mat_q,
-            'low_vram': shared.args.low_vram,
             'numa': shared.args.numa,
             'n_gpu_layers': shared.args.n_gpu_layers,
             'rope_freq_base': RoPE.get_rope_freq_base(shared.args.alpha_value, shared.args.rope_freq_base),
diff --git a/modules/llamacpp_model.py b/modules/llamacpp_model.py
index febb7229..92c679e6 100644
--- a/modules/llamacpp_model.py
+++ b/modules/llamacpp_model.py
@@ -80,7 +80,6 @@ class LlamaCppModel:
             'use_mmap': not shared.args.no_mmap,
             'use_mlock': shared.args.mlock,
             'mul_mat_q': shared.args.mul_mat_q,
-            'low_vram': shared.args.low_vram,
             'numa': shared.args.numa,
             'n_gpu_layers': shared.args.n_gpu_layers,
             'rope_freq_base': RoPE.get_rope_freq_base(shared.args.alpha_value, shared.args.rope_freq_base),
diff --git a/modules/loaders.py b/modules/loaders.py
index a667cb75..1b6bef06 100644
--- a/modules/loaders.py
+++ b/modules/loaders.py
@@ -92,7 +92,6 @@ loaders_and_params = OrderedDict({
         'n_batch',
         'threads',
         'no_mmap',
-        'low_vram',
         'mlock',
         'mul_mat_q',
         'llama_cpp_seed',
@@ -109,7 +108,6 @@ loaders_and_params = OrderedDict({
         'n_batch',
         'threads',
         'no_mmap',
-        'low_vram',
         'mlock',
         'mul_mat_q',
         'alpha_value',
diff --git a/modules/shared.py b/modules/shared.py
index ee06b5a7..01e82ee8 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -117,7 +117,6 @@ parser.add_argument('--use_double_quant', action='store_true', help='use_double_
 parser.add_argument('--threads', type=int, default=0, help='Number of threads to use.')
 parser.add_argument('--n_batch', type=int, default=512, help='Maximum number of prompt tokens to batch together when calling llama_eval.')
 parser.add_argument('--no-mmap', action='store_true', help='Prevent mmap from being used.')
-parser.add_argument('--low-vram', action='store_true', help='Low VRAM Mode')
 parser.add_argument('--mlock', action='store_true', help='Force the system to keep the model in RAM.')
 parser.add_argument('--mul_mat_q', action='store_true', help='Activate new mulmat kernels.')
 parser.add_argument('--cache-capacity', type=str, help='Maximum cache capacity. Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed.')
diff --git a/modules/ui.py b/modules/ui.py
index 568f0e37..6271b0d4 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -71,7 +71,6 @@ def list_model_elements():
         'threads',
         'n_batch',
         'no_mmap',
-        'low_vram',
         'mlock',
         'mul_mat_q',
         'n_gpu_layers',
diff --git a/modules/ui_model_menu.py b/modules/ui_model_menu.py
index 18a2bcb7..a562d1ed 100644
--- a/modules/ui_model_menu.py
+++ b/modules/ui_model_menu.py
@@ -107,7 +107,6 @@ def create_ui():
                             shared.gradio['no_mmap'] = gr.Checkbox(label="no-mmap", value=shared.args.no_mmap)
                             shared.gradio['mlock'] = gr.Checkbox(label="mlock", value=shared.args.mlock)
                             shared.gradio['numa'] = gr.Checkbox(label="numa", value=shared.args.numa, info='NUMA support can help on some systems with non-uniform memory access.')
-                            shared.gradio['low_vram'] = gr.Checkbox(label="low-vram", value=shared.args.low_vram)
                             shared.gradio['cpu'] = gr.Checkbox(label="cpu", value=shared.args.cpu)
                             shared.gradio['load_in_8bit'] = gr.Checkbox(label="load-in-8bit", value=shared.args.load_in_8bit)
                             shared.gradio['bf16'] = gr.Checkbox(label="bf16", value=shared.args.bf16)
diff --git a/requirements.txt b/requirements.txt
index 64aede85..9d519b97 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -31,8 +31,8 @@ bitsandbytes==0.41.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
 
 # llama-cpp-python (CPU only, AVX2)
-https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.7/llama_cpp_python-0.2.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.7/llama_cpp_python-0.2.7-cp310-cp310-win_amd64.whl; platform_system == "Windows"
+https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 
 # CUDA wheels
 https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
@@ -42,8 +42,8 @@ https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu117
 https://github.com/turboderp/exllamav2/releases/download/v0.0.4/exllamav2-0.0.4+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.4/exllamav2-0.0.4+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.0/flash_attn-2.3.0+cu117torch2.0cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.7+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.7+cu117-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu117-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.27+cu117-py3-none-any.whl
diff --git a/requirements_amd.txt b/requirements_amd.txt
index a7038063..b15e4d06 100644
--- a/requirements_amd.txt
+++ b/requirements_amd.txt
@@ -31,11 +31,11 @@ bitsandbytes==0.38.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows"
 
 # llama-cpp-python (CPU only, AVX2)
-https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.7/llama_cpp_python-0.2.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.7/llama_cpp_python-0.2.7-cp310-cp310-win_amd64.whl; platform_system == "Windows"
+https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 
 # AMD wheels
 https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+rocm5.4.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+rocm5.4.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.7+rocm5.4.2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.11+rocm5.4.2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+rocm5.4.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements_amd_noavx2.txt b/requirements_amd_noavx2.txt
index f7e97d55..d567d798 100644
--- a/requirements_amd_noavx2.txt
+++ b/requirements_amd_noavx2.txt
@@ -31,8 +31,8 @@ bitsandbytes==0.38.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows"
 
 # llama-cpp-python (CPU only, no AVX2)
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/basic/llama_cpp_python-0.2.7+cu117-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/basic/llama_cpp_python-0.2.7+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/basic/llama_cpp_python-0.2.11+cu117-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/basic/llama_cpp_python-0.2.11+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 
 # AMD wheels
 https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+rocm5.4.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements_apple_intel.txt b/requirements_apple_intel.txt
index 533c0c42..6a37726e 100644
--- a/requirements_apple_intel.txt
+++ b/requirements_apple_intel.txt
@@ -31,6 +31,7 @@ bitsandbytes==0.41.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
 
 # Mac wheels
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.7-cp310-cp310-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.7-cp310-cp310-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.7-cp310-cp310-macosx_13_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_13_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
diff --git a/requirements_apple_silicon.txt b/requirements_apple_silicon.txt
index 2e0f6153..76024e2f 100644
--- a/requirements_apple_silicon.txt
+++ b/requirements_apple_silicon.txt
@@ -31,6 +31,7 @@ bitsandbytes==0.41.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
 
 # Mac wheels
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.7-cp310-cp310-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.7-cp310-cp310-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.7-cp310-cp310-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
diff --git a/requirements_cpu_only.txt b/requirements_cpu_only.txt
index ce1d8693..39f7e7d9 100644
--- a/requirements_cpu_only.txt
+++ b/requirements_cpu_only.txt
@@ -31,5 +31,5 @@ bitsandbytes==0.41.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
 
 # llama-cpp-python (CPU only, AVX2)
-https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.7/llama_cpp_python-0.2.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.7/llama_cpp_python-0.2.7-cp310-cp310-win_amd64.whl; platform_system == "Windows"
+https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp310-cp310-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements_cpu_only_noavx2.txt b/requirements_cpu_only_noavx2.txt
index a11bb8e8..ec665001 100644
--- a/requirements_cpu_only_noavx2.txt
+++ b/requirements_cpu_only_noavx2.txt
@@ -31,5 +31,5 @@ bitsandbytes==0.41.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
 
 # llama-cpp-python (CPU only, no AVX2)
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/basic/llama_cpp_python-0.2.7+cu117-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/basic/llama_cpp_python-0.2.7+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/basic/llama_cpp_python-0.2.11+cu117-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/basic/llama_cpp_python-0.2.11+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements_noavx2.txt b/requirements_noavx2.txt
index 8c9bc51a..f0e3383d 100644
--- a/requirements_noavx2.txt
+++ b/requirements_noavx2.txt
@@ -31,8 +31,8 @@ bitsandbytes==0.41.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
 
 # llama-cpp-python (CPU only, no AVX2)
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/basic/llama_cpp_python-0.2.7+cu117-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/basic/llama_cpp_python-0.2.7+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/basic/llama_cpp_python-0.2.11+cu117-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/basic/llama_cpp_python-0.2.11+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 
 # CUDA wheels
 https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
@@ -42,8 +42,8 @@ https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu117
 https://github.com/turboderp/exllamav2/releases/download/v0.0.4/exllamav2-0.0.4+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.4/exllamav2-0.0.4+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.0/flash_attn-2.3.0+cu117torch2.0cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.7+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
-https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.7+cu117-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
+https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu117-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.27+cu117-py3-none-any.whl