Optimized llama.cpp for AMD Instinct MI50/MI60/Radeon VII (gfx906).

amdenterpriseai/aim-meta-llama-llama-3-1-8b-instruct

amdenterpriseai

Multilingual 8B parameter instruction-tuned language model for dialogue use cases.

biopython/biopython-tutorial

biopython

Biopython with Tutorial running on top of Jupyter (IPython Notebook) on port 9803

biopython/biopython-notebook

biopython

Biopython with a Jupyter (IPython Notebook) frontend on port 9803

Ready to use llama.cpp python server with OpenAI compatible API and autodownloader for HF models

Docker builds based on https://github.com/grinco/ollama-vulkan

Ollama with Intel GPU acceleration via IPEX-LLM, optimized for Arc discrete GPUs

Debian Based LLAMA.CPP Image Repository

Server apache-php-passenger

bnb hack