Question about GGUF
#4
by curiousgeez - opened
I read in the card that the model is geared towards nvidia, but is there any plan on releasing GGUF or supporting AMD or Intel GPUs now that you've released the preview?
Excited to see new U.S. models, looking forward to testing your release.
Why not try the QVB8 Inference Engine?
I can running the Ripple on DGX Spark, and it works great for coding with VS Code + Cline!
https://huggingface.co/addiesam/Ripple-65B-Preview-QVB8R-1e-3
I actually tested an Intel GPU with a Qwen 2.7B model, but I haven't built the engine for Ripple on it yet. I don't currently have the resources to get an Intel GPU for further testing. That said, the underlying mathematical theory and implementation are entirely independent of the specific GPU hardware.