docker pull hiyouga/verl:ngc-th2.8.0-cu12.9-vllm0.11.0 docker run -it --ipc=host --gpus=all hiyouga/verl:ngc-th2.8.0-cu12.9-vllm0.11.0 Edit vllm_serve.sh to configure the model, GPU IDs, port, and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results