# Torch
torch --index-url https://download.pytorch.org/whl/cu121

# Exllamav2

# Windows
https://github.com/turboderp/exllamav2/releases/download/v0.0.10/exllamav2-0.0.10+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/turboderp/exllamav2/releases/download/v0.0.10/exllamav2-0.0.10+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"

# Linux
https://github.com/turboderp/exllamav2/releases/download/v0.0.10/exllamav2-0.0.10+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/v0.0.10/exllamav2-0.0.10+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

# Pip dependencies
fastapi
pydantic < 2,>= 1
PyYAML
progress
uvicorn

# Flash attention v2

# Windows FA2 from https://github.com/jllllll/flash-attention/releases
https://github.com/jllllll/flash-attention/releases/download/v2.3.6/flash_attn-2.3.6+cu121torch2.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/flash-attention/releases/download/v2.3.6/flash_attn-2.3.6+cu121torch2.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"

# Linux FA2 from https://github.com/Dao-AILab/flash-attention/releases
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.6/flash_attn-2.3.6+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/v2.3.6/flash_attn-2.3.6+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"