LLaMA C++ with GPT OSS Implementation on GPU Offload

This image has been deprecated since the release of OPEA v1.2.

llama_meta_2

Debian Based Ollama Image Repository

CPU Only Image for Ollama

Base images for LLAMA

chainguard/python

chainguard

Build, ship and run secure software with Chainguard's low-to-zero CVE container images.

pool

https://github.com/knguyen298/llama-swap-gfx906

llama.cpp for quantizing and inferencing large language models in C++

Llama.cpp server bundled with 2 general small AI.