requirements_reranker_qwen3_transformers_packed.txt
412 Bytes
# Isolated dependencies for qwen3_transformers_packed reranker backend.
#
# Keep this stack aligned with the validated CUDA runtime on our hosts.
# On this machine, torch 2.11.0 + cu130 fails CUDA init, while torch 2.10.0 + cu128 works.
# We also cap transformers <5 to stay on the same family as the working vLLM score env.
-r requirements_reranker_qwen3_transformers.txt
torch==2.10.0
transformers>=4.51.0,<5