ipex-llm
ipex-llm copied to clipboard
intel-analytics
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, Phi, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Ma...
Since we are moving quickly in main branch and the API might be unstable from time to time, we need to help our users to install nightly build version rather...
## Description ### 1. Why the change? model save on FL Server need to be encrypted. ### 2. User API changes None ### 3. Summary of the change Support encryption...
## Description Besides submit as spark job, BigDL k8s examples can also run as SparkApplication, which is a custom k8s resource. It is supported by custom controller spark-operator and scheduler...
## Description Add save/load fundamental examples for optimized Pytorch model. ### 1. Why the change? related issue: #5773 ### 2. User API changes N/A ### 3. Summary of the change...
## Description Update https://bigdl.readthedocs.io/en/latest/doc/Nano/QuickStart/pytorch_inference.html with InferenceOptimizer ### 1. Why the change? As we have deprecated Trainer.trace / Trainer.quantize, we need to change our documentation too. ### 2. User API changes...
## Description This PR is to add `compile_args_creator` support in distributed training of tf2 ray/pyspark estiamtor.
## Description Add OpenVINO tutorial test scripts and add them to github workflow as part of nano-notebook-tests. ### 1. Why the change? As mentioned in PR #5832, the OpenVINO fundamental...
When I want to call `spark_df_to_pd_sparkxshards()` to transform the `spark dataframe` to `sparkxshards` after the `join()` operation, an error occurs in the function. It shows `Must pass schema or at...
## Description When setting `LD_PRELOAD`, the `bigdl-nano-init` script prefers to look for `libtcmalloc.so` and `libjemalloc.so` in `$LIB_DIR` directory, which is `${CONDA_PREFIX}/lib`. However, these .so files should be in `${NANO_DIR}/libs` directory....
## Description Add zsh support for `bigdl-nano-init` script fix #5751
Metadata
Owner
Metadata
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, Phi, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Ma...