This repo provides container images for llama.cpp server and ollama server for Intel CPU, GPU and NPU (based on intelanalytics/ipex-llm-inference-cpp-xpu) that are ready-to-run.
| Name | Container Image | README |
|---|---|---|
| llama.cpp server | ghcr.io/lirc572/ipex-llm-serve-llama.cpp | README |
| ollama server | ghcr.io/lirc572/ipex-llm-serve-ollama | README |