forked from Karylab-cklius/vllm
The lockfile was compiled with --torch-backend cu129, pinning torch==2.10.0+cu129. This breaks Docker builds that use CUDA_VERSION=12.8 because the cu128 PyTorch index does not carry +cu129 wheels. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>