ipex-llm
ipex-llm copied to clipboard
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...
## Description Refer to the report by customers, the program reported `list index out of range` error if they do not specify the HDFS port. Because that the port is...
Use spark backend got error:NotImplementedError: Saving the model to HDF5 format requires the model to be a Functional model or a Sequential model. It does not work for subclassed models,...
## Description Add How-to-Guides, and help users train forecaster. ### 1. Why the change? Make our doc more friendly. ### 2. User API changes No changed. ### 3. Summary of...
## Description This is a preview of a small part of the entire project before adding python type hint, including templates, tools and modification processes ### 1. Why the change?...
Add pytorch lightning nano example: 1. channel last example 2. cv data pipeline example
SDL no longer recommend AES 128/192. Need to change to 256 for AES default key length. Note: AES-256 is required because use of AES-128 or AES-192 exposes the implementation to...
## Possible Imporvements for ReadtheDocs Nano Section ### 1. Major Issues #### 1.1 [BigDL-Nano TensorFlow Inference Overview](https://bigdl.readthedocs.io/en/latest/doc/Nano/QuickStart/pytorch_inference.html) For this page, most of contents seems to be directly copied from "BigDL-Nano...
## Description unzip: cannot find or open tmp/data/object-detection-coco.zip, tmp/data/object-detection-coco.zip.zip ### 1. Why the change? ### 2. User API changes ### 3. Summary of the change ### 4. How to test?...
## Description update the simple query example with PPMLContext in both python and scala api. add more usage example and dataframe operation example. ### 1. Why the change? the old...
## Description In fit, if input is dataframe, we will do repartition if partition < num workers when converting to SparkXShards. After converting to SparkXShards, the data should have num_partitions...