acd77d9e87
* fix: remove BIGDL_LLM_XMX_DISABLED in mddocs * fix: remove set SYCL_CACHE_PERSISTENT=1 in example * fix: remove BIGDL_LLM_XMX_DISABLED in workflows * fix: merge igpu and A-series Graphics * fix: remove set BIGDL_LLM_XMX_DISABLED=1 in example * fix: remove BIGDL_LLM_XMX_DISABLED in workflows * fix: merge igpu and A-series Graphics * fix: textual adjustment * fix: textual adjustment * fix: textual adjustment
124 lines
4.5 KiB
Markdown
124 lines
4.5 KiB
Markdown
# Save/Load Low-Bit Models with IPEX-LLM Optimizations
|
|
|
|
In this directory, you will find example on how you could save/load models with IPEX-LLM INT4 optimizations on Llama2 models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) and [meta-llama/Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) as reference Llama2 models.
|
|
|
|
## 0. Requirements
|
|
To run this example with IPEX-LLM, we have some recommended requirements for your machine, please refer to [here](../../README.md#system-support) for more information.
|
|
|
|
## Example: Save/Load Model in Low-Bit Optimization
|
|
In the example [generate.py](./generate.py), we show a basic use case of saving/loading model in low-bit optimizations to predict the next N tokens using `generate()` API. Also, saving and loading operations are platform-independent, so you could run it on different platforms.
|
|
### 1. Install
|
|
#### 1.1 Installation on Linux
|
|
We suggest using conda to manage environment:
|
|
```bash
|
|
conda create -n llm python=3.11
|
|
conda activate llm
|
|
# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
|
|
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
|
|
```
|
|
|
|
#### 1.2 Installation on Windows
|
|
We suggest using conda to manage environment:
|
|
```bash
|
|
conda create -n llm python=3.11 libuv
|
|
conda activate llm
|
|
# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
|
|
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
|
|
```
|
|
|
|
### 2. Configures OneAPI environment variables for Linux
|
|
|
|
> [!NOTE]
|
|
> Skip this step if you are running on Windows.
|
|
|
|
This is a required step on Linux for APT or offline installed oneAPI. Skip this step for PIP-installed oneAPI.
|
|
|
|
```bash
|
|
source /opt/intel/oneapi/setvars.sh
|
|
```
|
|
|
|
### 3. Runtime Configurations
|
|
For optimal performance, it is recommended to set several environment variables. Please check out the suggestions based on your device.
|
|
#### 3.1 Configurations for Linux
|
|
<details>
|
|
|
|
<summary>For Intel Arc™ A-Series Graphics and Intel Data Center GPU Flex Series</summary>
|
|
|
|
```bash
|
|
export USE_XETLA=OFF
|
|
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
|
|
export SYCL_CACHE_PERSISTENT=1
|
|
```
|
|
|
|
</details>
|
|
|
|
<details>
|
|
|
|
<summary>For Intel Data Center GPU Max Series</summary>
|
|
|
|
```bash
|
|
export LD_PRELOAD=${LD_PRELOAD}:${CONDA_PREFIX}/lib/libtcmalloc.so
|
|
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
|
|
export SYCL_CACHE_PERSISTENT=1
|
|
export ENABLE_SDP_FUSION=1
|
|
```
|
|
> Note: Please note that `libtcmalloc.so` can be installed by `conda install -c conda-forge -y gperftools=2.10`.
|
|
</details>
|
|
|
|
<details>
|
|
|
|
<summary>For Intel iGPU</summary>
|
|
|
|
```bash
|
|
export SYCL_CACHE_PERSISTENT=1
|
|
```
|
|
|
|
</details>
|
|
|
|
#### 3.2 Configurations for Windows
|
|
<details>
|
|
|
|
<summary>For Intel iGPU and Intel Arc™ A-Series Graphics</summary>
|
|
|
|
```cmd
|
|
set SYCL_CACHE_PERSISTENT=1
|
|
```
|
|
|
|
</details>
|
|
|
|
|
|
> [!NOTE]
|
|
> For the first time that each model runs on Intel iGPU/Intel Arc™ A300-Series or Pro A60, it may take several minutes to compile.
|
|
|
|
### 4. Running examples
|
|
|
|
If you want to save the optimized low-bit model, run:
|
|
```
|
|
python ./generate.py --save-path path/to/save/model
|
|
```
|
|
|
|
If you want to load the optimized low-bit model, run:
|
|
```
|
|
python ./generate.py --load-path path/to/load/model
|
|
```
|
|
|
|
In the example, several arguments can be passed to satisfy your requirements:
|
|
|
|
- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the Llama2 model to be downloaded, or the path to the ModelScope checkpoint folder. It is default to be `'meta-llama/Llama-2-7b-chat-hf'`.
|
|
- `--save-path`: argument defining the path to save the low-bit model. Then you can load the low-bit directly.
|
|
- `--load-path`: argument defining the path to load low-bit model.
|
|
- `--prompt PROMPT`: argument defining the prompt to be inferred (with integrated prompt format for chat). It is default to be `'What is AI?'`.
|
|
- `--n-predict N_PREDICT`: argument defining the max number of tokens to predict. It is default to be `32`.
|
|
|
|
#### Sample Output
|
|
#### [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)
|
|
```log
|
|
Inference time: xxxx s
|
|
-------------------- Output --------------------
|
|
### HUMAN:
|
|
What is AI?
|
|
|
|
### RESPONSE:
|
|
|
|
AI is a term used to describe the development of computer systems that can perform tasks that typically require human intelligence, such as understanding natural language, recognizing images
|
|
```
|