Spaces:
Running
Running
Download processor/requirements-vllm.txt from Stouching-Robotics/DataFlowing: direct link, hf CLI and curl.
- Browser
- Download file 262 Bytes
-
https://huggingface.co/spaces/Stouching-Robotics/DataFlowing/resolve/main/processor/requirements-vllm.txt
- Command line
-
hf download hf://spaces/Stouching-Robotics/DataFlowing/processor/requirements-vllm.txt
-
curl -L -o requirements-vllm.txt https://huggingface.co/spaces/Stouching-Robotics/DataFlowing/resolve/main/processor/requirements-vllm.txt
262 Bytes
| # Local VLM runtime (vLLM) — GPU-only, NEVER merge into requirements-linux.txt / | |
| # requirements-windows.txt. vLLM pulls its matching torch/CUDA build | |
| # transitively; do not pin torch here. SM120 (RTX 5090) FP8 flags live in | |
| # scripts/run_vllm.sh. | |
| vllm==0.27.1 | |