Baye Dieng

Implement Virtio Block Driver

3

## See #48

MaxPool2d not outputting proper shape on burn-ndarray and burn-wgpu backends

9

**Describe the bug** Something seems to be wrong with the implementation of maxpool2d's backends. When testing against torch tensors I am getting different shapes. The burn backends aren't outputting the...

Support MPS on Macos devices

3

This project would have a significant speed boost on mac if the demucs model were to use mps instead of cpu in a similar way that the windows binary uses...

Metal Backend not properly loading large models at 16GB of RAM

15

Ran Phi 2 model with the metal features enabled and seems to hang with about 7% of GPU usage from Activity monitor. This seems to be recent as it ran...

Add Llama.cpp Support

9

This PR adds support for Llama.cpp and closes #167.

This PR is meant to add LLama CPP Support using the ggml inference engine. For the sake of simplicity, this PR will take Q8(8-bit) format GGUF Files, implementing the LLAMA...