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...
If a partition of an XShards has more than one pandas dataframe, the `to_spark_df` function will only process the first pdf. Error code: https://github.com/intel-analytics/BigDL/blob/main/python/orca/src/bigdl/orca/data/shard.py#L583
## Description Fix https://github.com/intel-analytics/BigDL/issues/5877. Add logic to check if there is empty partition of spark dataframe, if there is and if `spark_df_to_pd_sparkxshards` is called, will throw exception.
The problem occurred when importing `Model` from `bigdl.nano.tf.keras` after we have used tensorflow for creating datasets, etc. Example problematic code: ```python import tensorflow as tf import tensorflow_datasets as tfds def...
## Description Add tensorflow known issue for inter op parallelism cannot be modified
add datails into doc 1. updated guide to create Azure VM with SGX. 2. updated cammand (provided by Azure Portal) to pull PPML image from Azure container registry. 3. added...
Add NCF pytorch examples : `train_data_loader.py` and `train_xshards.py` to the `NCF` directory, with a shared NCF-model `model.py`. 1.The `train_data_loader.py` example takes `data_loader` as the input of the model, supporting fitting...
Hi, I am trying to run a Fashion MNIST sample code given in BigDL repo on Azure Databricks spark cluster environment. Sample code link is here : https://github.com/intel-analytics/BigDL/blob/main/python/orca/colab-notebook/examples/fashion_mnist_bigdl.ipynb **Cluster Configuration:**...
## Description Update Databricks user guide, before, user need to download and upload packages to get BigDL env ready on Databricks, and config by this way, the ray worker still...
We can use `OpenVINOModel` API to load an OpenVINO model and do inference in Nano, so in this case, there is no need to install nano with frameworks like TF...
https://github.com/intel-analytics/BigDL/pull/5763#issuecomment-1254428840
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...