From d7f1bc102b0a75cce239fcf901305dfb055dd350 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Mon, 20 Nov 2023 16:36:38 -0300 Subject: [PATCH] Fix "Illegal instruction" bug in llama.cpp CPU only version (#4677) --- requirements.txt | 16 ++++++++-------- requirements_amd.txt | 16 ++++++++-------- requirements_cpu_only.txt | 16 ++++++++-------- 3 files changed, 24 insertions(+), 24 deletions(-) diff --git a/requirements.txt b/requirements.txt index 6377723e..f96c8907 100644 --- a/requirements.txt +++ b/requirements.txt @@ -27,14 +27,14 @@ 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/v0.2.18/llama_cpp_python-0.2.18-cp311-cp311-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp310-cp310-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp39-cp39-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp38-cp38-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" +https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-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/cpu/llama_cpp_python-0.2.18+cpuavx-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/cpu/llama_cpp_python-0.2.18+cpuavx-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/cpu/llama_cpp_python-0.2.18+cpuavx-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/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" +https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" # CUDA wheels https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" diff --git a/requirements_amd.txt b/requirements_amd.txt index 8f8f44ff..fae59a0a 100644 --- a/requirements_amd.txt +++ b/requirements_amd.txt @@ -27,14 +27,14 @@ 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/v0.2.18/llama_cpp_python-0.2.18-cp311-cp311-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp310-cp310-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp39-cp39-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp38-cp38-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" +https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-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/cpu/llama_cpp_python-0.2.18+cpuavx-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/cpu/llama_cpp_python-0.2.18+cpuavx-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/cpu/llama_cpp_python-0.2.18+cpuavx-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/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" +https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" # AMD wheels https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" diff --git a/requirements_cpu_only.txt b/requirements_cpu_only.txt index 56747a70..8cccafa9 100644 --- a/requirements_cpu_only.txt +++ b/requirements_cpu_only.txt @@ -27,11 +27,11 @@ 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/v0.2.18/llama_cpp_python-0.2.18-cp311-cp311-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp310-cp310-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp39-cp39-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp38-cp38-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" -https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" +https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-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/cpu/llama_cpp_python-0.2.18+cpuavx-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/cpu/llama_cpp_python-0.2.18+cpuavx-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/cpu/llama_cpp_python-0.2.18+cpuavx-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/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" +https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"