ardge/mirrored-llama.cpp repository overview

Unofficial mirror of ghcr.io/ggml-org/llama.cpp, published for hosts that pull from Docker Hub. Not an official release.

• Upstream project: https://github.com/ggml-org/llama.cpp⁠
• Each tag is the upstream tag of the same name, copied unchanged: the manifest digest is upstream's own, and a tag is never republished.
• License: MIT (https://github.com/ggml-org/llama.cpp/blob/master/LICENSE⁠); the CUDA, oneAPI and ROCm runtime layers keep their own licenses, listed in https://github.com/ardge-labs/arx-artifact-mirror#source-and-license⁠