# Core vLLM-compatible dependencies with Molmo accuracy setup (tested on L40)
torch==2.5.1
torchvision==0.20.1
transformers==4.48.1
tokenizers==0.21.0
tiktoken==0.7.0
vllm==0.7.0

# Optional but recommended for improved performance and stability
triton==3.1.0
xformers==0.0.28.post3
uvloop==0.21.0
protobuf==5.29.3
openai==1.60.2
opencv-python-headless==4.11.0.86
pillow==10.4.0

# Installed FlashAttention (for float16 only)
flash-attn>=2.5.6  # Not used in float32, but should be documented