GitHub - 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[2025/05] You can now run DeepSeek V3/R1 671B and Qwen3MoE 235B models with just 1 or 2 Intel Arc GPU (such as A770 or B580) using FlashMoE in ipex-llm. [2025/04] We released ipex-llm 2.2.0, which includes Ollama Portable Zip and llama.cpp Portable Zip. [2025/04] We added support of PyTorch 2.6 for Intel GPU. [2025/03] We added support for Gemma3 model in the latest llama.cpp Portable Zip. [2025/0
