Giters

intel / ipex-llm

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc.

Repository from Github https://github.comintel/ipex-llmRepository from Github https://github.comintel/ipex-llm

Docker Image not updated

tomalta opened this issue · comments

commented

I'm seeing the Docker images for GPU inference being updated on the Docker Hub, but the images do not cointain any significant change, like updates to Ollama or old Pytorch libraries.

Is it gonna receive a significant update that brings up Ollama to 0.6?

commented

Hi @tomalta, we are currently working on supporting 0.6.x ollama.

commented

There will be a notification about it? Either on the Github main page or any others? As mentioned there are many updates pushed to the Docker image and they don't have any details in their page. Thanks for your work.

commented

Yeah, we will post a notification on the IPEX-LLM GitHub main page :)