When an open source library brings down production and your boss wants to sue

[text] README.md FauxPilot This is an attempt to build a locally hosted version of GitHub Copilot. It uses the SalesForce CodeGen models inside of NVIDIAs Triton Inference Server with the FasterTransformer backend. Prerequisites Youll need LRIl g e dockercompose 1.28 An NVIDIA GPU with enough VRAM to run the model you want. e nvidiadocker Note that the VRAM requirements listed by setup.sh are total if you have multiple GPUs you can split the model across them. So if you have two NVIDIA RTX 3080 GPUs you should be able to run the 6B model by putting half on each R Support and Warranty