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...
## Description add `gendt_feature` function to `xshards_dataset` ### User API ``` shards_tmp = read_csv(file_name) # interval = day tsdata = XShardsTSDataset.from_xshards(shards_tmp, dt_col="datetime", target_col="value", extra_feature_col=["extra feature"], id_col="id") features = ['DAY',] tsdata.gen_dt_feature(features=features)...
## Description Read the data set in `ncf_orca.py` into spark dataframe, process it, generate negative samples, and change the model to a binary model. ### 1. Why the change? Support...
Nowdays, input data types for different methods in BaseForecaster and AutoformerForecaster is different and is confusing. The following table lists the support data types of each method: | Method |...
When importing both openvino and intel-tensorflow > 2.7, the following code will raise an error: `RuntimeError: dimension (-1) in node dim must be greater or equal to -1: at offset`...
## Description Fix command injection during model conversion: Details: the system passes user-supplied input directly to exec(), eval(), and os.system() methods without validation, which could result in command injection. ###...
## Description We need to align function in BaseForecaster and AutoformerForecaster synchronously. ### 1. Why the change? https://github.com/intel-analytics/BigDL/issues/5834 ### 2. User API changes ``` from bigdl.chronos.forecaster import AutoformerForecaster forecaster =...
## Description ### 1. Why the change? ### 2. User API changes ### 3. Summary of the change ### 4. How to test? - [ ] N/A - [ ]...
## Description ### 1. Why the change? Add fundamental notebook examples to show how to run sync and async inference on OpenVINO model using Nano. ### 2. User API changes...
## Background We have met with a large amount of different time series, and we should detect the low-quality data and provide suggestion (e.g. call `.impute` or `.resample`) during the...
Description: Currently, we have supported the `nbeats` model, some details are given below: * `nbeats` is extremely fast for training and inference. * Friendly to time series datasets with seasonal...
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...