exllama / requirements.txt
pabl-o-ce
repo init
fc9eab8
raw
history blame
323 Bytes
huggingface_hub==0.22.2
tokenizers
numpy==2.1.2
https://github.com/turboderp/exllamav2/releases/download/v0.2.3/exllamav2-0.2.3+cu121.torch2.3.1-cp310-cp310-linux_x86_64.whl
https://github.com/Dao-AILab/flash-attention/releases/download/v2.6.3/flash_attn-2.6.3+cu123torch2.4cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
jinja2