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 PPML assembly package * start FLServer is supported from scripts in this package * To use it, 1. get assembly folder 2. `source setup-env.sh` 3. run...
## Description `bigdl.nano.openvino.OpenVINOModel` has now provided limited features for users and few notifications about current status. We can only simply run inference like： ```python from bigdl.nano.openvino import OpenVINOModel openvino_model =...
## Description This issue mainly describes a new distributed data input, which could be used the same as the standard Pytorch Dataloader. ## Motivation * Pure Ray pipeline needs a...
## Description ### 1. Why the change? To help users who pursue a quick use of Chronos build a docker image with dependencies installed and unitest examples passed. Users can...
#### 1. Why we need this? Sync with `BasepytorchForecaster`. #### 2. What is the change? 1. support input `tfdataset` and `tsdataset` directly. 2. add from_tsdataset method(like load) #### 3. How...
Add tutorials for submitting and running programs on yarn. - [x] rename `spark-submit-with-bigdl` to `bigdl-submit` - [x] add a multiple python files demo - [x] built-in - [x] bigdl-submit -...
Add ModelCheckpoint callbacks with training using `estimator.fit( )` to save a model in a checkpoint file. - [x] Save model and weights only. - [x] Save and load model weights.
This Exception only happens when DataFrame's record number is less than the partition number. for example, DataFrame `df` only contain 3 Row, when we config --master 'local[n]' or use `df.repartition(n)`...
The pasted code will throw the following error: ``` Traceback (most recent call last): File "/home/yang/miniconda3/envs/nano-pytorch-2/lib/python3.7/site-packages/neural_compressor/experimental/quantization.py", line 151, in execute self.strategy.traverse() File "/home/yang/miniconda3/envs/nano-pytorch-2/lib/python3.7/site-packages/neural_compressor/strategy/strategy.py", line 392, in traverse tune_cfg, self.model, self.calib_dataloader,...
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...