Refactored codebase - now a single unified turbopilot binary that provides support for codegen and starcoder style models.

Support for starcoder, wizardcoder and santacoder models

Support for CUDA 11 and 12

Seems interesting, looks like it supports wizardcoder with GPU offloading, if starcoder also has GPU offloading then that would be great but I would need to test. If it also works with the new stabilityAI coding models that would be very interesting