LTX-2.5-Text-Encoder-4bit-8GB / requirements.txt
topabaem's picture
Ship the loader, so the quickstart can actually run
d710727 verified
Raw
History Blame Contribute Delete
543 Bytes
# Everything the loader needs. No build step, no custom CUDA kernels.
#
# IMPORTANT for older GPUs: the default wheel on PyPI is now a cu130 build, and
# cu130 dropped Volta (sm_70). On a V100 it fails at the first kernel launch
# with "no kernel image is available for execution on the device" - after
# torch.cuda.is_available() has already returned True. For sm_70 install a cu128
# build instead:
# pip install torch --index-url https://download.pytorch.org/whl/cu128
torch>=2.1
transformers>=5.12
accelerate
safetensors
huggingface_hub