| # Install a CUDA-enabled PyTorch build matching your host first. | |
| # The tested worker used torch 2.10.0+cu128 on Linux. | |
| transformers==5.17.0 | |
| peft==0.21.0 | |
| accelerate==1.15.0 | |
| Pillow==12.3.0 | |
| fastapi==0.141.1 | |
| starlette==1.6.0 | |
| pydantic==2.13.5 | |
| uvicorn>=0.30,<1 | |
| huggingface_hub>=1.32,<2 | |
| triton>=3.7.1 | |
| flash-linear-attention[cuda] | |