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.
e7ca47e837
* feat: SReLU and ActivityRegularization support * fix: update doc * fix: refactor the weights and gradWeights of SReLU * fix: serialization for srelu * fix: backward computing errors * fix: ActivityRegularization to layer * fix: change test location * fix: add python api * fix: shared axes have not consider enough |
||
|---|---|---|