requirements.txt

# Notes:
#   The base image `vllm/vllm-openai:v0.8.5` already ships:
#     - torch 2.6 / torchaudio / torchvision (CUDA 12.4 build)
#     - vllm 0.8.5
#     - transformers (compatible with vllm 0.8.5)
#     - flash_attn 2.7.x (used by vllm's flash-attn backend)
#   Re-installing any of them here triggers a full source build of flash_attn
#   (no PyPI wheel available), which OOM-kills the HF Space *build*
#   container. Keep this list to lightweight, app-only dependencies.
#
# IMPORTANT version pin:
#   The transformers shipped in vllm 0.8.5 requires huggingface-hub<1.0.
#   Without an explicit upper bound here, pip happily upgrades
#   huggingface-hub to 1.x (released 2025-Q4), which then makes
#   `import transformers` -> `import vllm` fail at container start with:
#     ImportError: huggingface-hub>=0.30.0,<1.0 is required ...
huggingface-hub>=0.30.0,<1.0
librosa>=0.11.0
nnAudio>=0.3.3
gradio>=4.44
wheel>=0.45.1

# Required by megatron/tokenizer.py (OmegaConf.load on the vocab file).
# Pure-Python, no native deps -> safe for the locked transformers/torch tree.
omegaconf>=2.3,<3.0

# Required by:
#   - mucodec/descript_quantize3.py
#   - mucodec/.../musicfm/model/musicfm_25hz.py
#   - mucodec/.../musicfm/modules/{conv,random_quantizer}.py
# Pure-Python, zero deps. The vllm base image often already bundles it,
# but listing it explicitly removes the guesswork.
einops>=0.7