Skip to content

Commit

Permalink
Bump llama-cpp-python, remove python 3.8/3.9, cuda 11.7 (oobabooga#5397)
Browse files Browse the repository at this point in the history
  • Loading branch information
@oobabooga
oobabooga authored Jan 30, 2024
1 parent 528318b commit 89f6036
Show file tree
Hide file tree
Showing 10 changed files with 60 additions and 162 deletions.
7 changes: 2 additions & 5 deletions Colab-TextGen-GPU.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -65,12 +65,9 @@
" torver = torch.__version__\n",
" print(f\"TORCH: {torver}\")\n",
" is_cuda118 = '+cu118' in torver # 2.1.0+cu118\n",
" is_cuda117 = '+cu117' in torver # 2.0.1+cu117\n",
"\n",
" textgen_requirements = open('requirements.txt').read().splitlines()\n",
" if is_cuda117:\n",
" textgen_requirements = [req.replace('+cu121', '+cu117').replace('+cu122', '+cu117').replace('torch2.1', 'torch2.0') for req in textgen_requirements]\n",
" elif is_cuda118:\n",
" if is_cuda118:\n",
" textgen_requirements = [req.replace('+cu121', '+cu118').replace('+cu122', '+cu118') for req in textgen_requirements]\n",
" with open('temp_requirements.txt', 'w') as file:\n",
" file.write('\\n'.join(textgen_requirements))\n",
Expand Down Expand Up @@ -130,4 +127,4 @@
"outputs": []
}
]
}
}
7 changes: 2 additions & 5 deletions one_click.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -299,7 +299,6 @@ def update_requirements(initial_installation=False):
torver = torch_version()
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
is_cpu = '+cpu' in torver # 2.0.1+cpu
Expand All @@ -320,11 +319,9 @@ def update_requirements(initial_installation=False):

# Prepare the requirements file
textgen_requirements = open(requirements_file).read().splitlines()
if is_cuda117:
textgen_requirements = [req.replace('+cu121', '+cu117').replace('+cu122', '+cu117').replace('torch2.1', 'torch2.0') for req in textgen_requirements]
elif is_cuda118:
if is_cuda118:
textgen_requirements = [req.replace('+cu121', '+cu118').replace('+cu122', '+cu118') for req in textgen_requirements]
if is_windows() and (is_cuda117 or is_cuda118): # No flash-attention on Windows for CUDA 11
if is_windows() and is_cuda118: # No flash-attention on Windows for CUDA 11
textgen_requirements = [req for req in textgen_requirements if 'jllllll/flash-attention' not in req]

with open('temp_requirements.txt', 'w') as file:
Expand Down
52 changes: 12 additions & 40 deletions requirements.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -29,67 +29,39 @@ 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/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp311-cp311-manylinux_2_31_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/cpu/llama_cpp_python-0.2.36+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"

# llama-cpp-python (CUDA, no tensor cores)
https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+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/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+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/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+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/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.36+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.36+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.36+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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.36+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

# llama-cpp-python (CUDA, tensor cores)
https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+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/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+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/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+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/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.36+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.36+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.36+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/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.36+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

# CUDA wheels
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+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/v0.6.0/auto_gptq-0.6.0+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/v0.6.0/auto_gptq-0.6.0+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/v0.6.0/auto_gptq-0.6.0+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/v0.0.12/exllamav2-0.0.12+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+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/v0.0.12/exllamav2-0.0.12+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/v0.0.12/exllamav2-0.0.12+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/v0.0.12/exllamav2-0.0.12+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+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/v2.3.4/flash_attn-2.3.4+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/v2.3.4/flash_attn-2.3.4+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/v2.3.4/flash_attn-2.3.4+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/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==0.1.8; platform_system == "Linux" or platform_system == "Windows"
Loading

0 comments on commit 89f6036

Please sign in to comment.