ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

[LLM] Small updates to Win GPU Install Doc (#10199)

Browse source 
* Make Offline installer as default for win gpu doc for oneAPI

* Small other fixes
This commit is contained in:
Yuwen Hu 2024-02-21 17:58:40 +08:00 committed by GitHub
parent 5b387bb71a
commit 94cb16fe40
3 changed files with 7 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -162,6 +162,7 @@ Over 40 models have been optimized/verified on `bigdl-llm`, including *LLaMA/LLa
| Baichuan2 | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/baichuan2) | [link](python/llm/example/GPU/HF-Transformers-AutoModels/Model/baichuan2) | | Baichuan2 | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/baichuan2) | [link](python/llm/example/GPU/HF-Transformers-AutoModels/Model/baichuan2) |
| InternLM | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/internlm) | [link](python/llm/example/GPU/HF-Transformers-AutoModels/Model/internlm) | | InternLM | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/internlm) | [link](python/llm/example/GPU/HF-Transformers-AutoModels/Model/internlm) |
| Qwen | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/qwen) | [link](python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen) | | Qwen | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/qwen) | [link](python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen) |
| Qwen1.5 | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/qwen1.5) | [link](python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen1.5) |
| Qwen-VL | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/qwen-vl) | [link](python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen-vl) | | Qwen-VL | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/qwen-vl) | [link](python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen-vl) |
| Aquila | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/aquila) | [link](python/llm/example/GPU/HF-Transformers-AutoModels/Model/aquila) | | Aquila | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/aquila) | [link](python/llm/example/GPU/HF-Transformers-AutoModels/Model/aquila) |
| Aquila2 | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/aquila2) | [link](python/llm/example/GPU/HF-Transformers-AutoModels/Model/aquila2) | | Aquila2 | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/aquila2) | [link](python/llm/example/GPU/HF-Transformers-AutoModels/Model/aquila2) |
@ -187,7 +188,6 @@ Over 40 models have been optimized/verified on `bigdl-llm`, including *LLaMA/LLa
| Bark | [link](python/llm/example/CPU/PyTorch-Models/Model/bark) | [link](python/llm/example/GPU/PyTorch-Models/Model/bark) | | Bark | [link](python/llm/example/CPU/PyTorch-Models/Model/bark) | [link](python/llm/example/GPU/PyTorch-Models/Model/bark) |
| SpeechT5 | | [link](python/llm/example/GPU/PyTorch-Models/Model/speech-t5) | | SpeechT5 | | [link](python/llm/example/GPU/PyTorch-Models/Model/speech-t5) |
| Ziya-Coding-34B-v1.0 | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/ziya) | | | Ziya-Coding-34B-v1.0 | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/ziya) | |
| Qwen1.5 | [link](python/llm/example/CPU/HF-Transformers-AutoModels/Model/qwen1.5) | [link](python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen1.5) |
***For more details, please refer to the `bigdl-llm` [Document](https://test-bigdl-llm.readthedocs.io/en/main/doc/LLM/index.html), [Readme](python/llm), [Tutorial](https://github.com/intel-analytics/bigdl-llm-tutorial) and [API Doc](https://bigdl.readthedocs.io/en/latest/doc/PythonAPI/LLM/index.html).*** ***For more details, please refer to the `bigdl-llm` [Document](https://test-bigdl-llm.readthedocs.io/en/main/doc/LLM/index.html), [Readme](python/llm), [Tutorial](https://github.com/intel-analytics/bigdl-llm-tutorial) and [API Doc](https://bigdl.readthedocs.io/en/latest/doc/PythonAPI/LLM/index.html).***

8
docs/readthedocs/source/doc/LLM/Overview/install_gpu.md
View file

@ -24,6 +24,11 @@ Intel® oneAPI Base Toolkit 2024.0 installation methods:
```eval_rst ```eval_rst
.. tabs:: .. tabs::
.. tab:: Offline installer
Download and install `Intel® oneAPI Base Toolkit <https://www.intel.com/content/www/us/en/developer/tools/oneapi/base-toolkit-download.htm?operatingsystem=window&distributions=offline>`_ version 2024.0 through Offline Installer.
During installation, you could just continue with "Recommended Installation". If you would like to continue with "Custom Installation", please note that oneAPI Deep Neural Network Library, oneAPI Math Kernel Library, and oneAPI DPC++/C++ Compiler are required, the other components are optional.
.. tab:: PIP installer .. tab:: PIP installer
Pip install oneAPI in your working conda environment. Pip install oneAPI in your working conda environment.
@ -33,9 +38,6 @@ Intel® oneAPI Base Toolkit 2024.0 installation methods:
.. note:: .. note::
Activating your working conda environment will automatically configure oneAPI environment variables. Activating your working conda environment will automatically configure oneAPI environment variables.
.. tab:: Offline installer
Download and install `Intel® oneAPI Base Toolkit <https://www.intel.com/content/www/us/en/developer/tools/oneapi/base-toolkit-download.html>`_ version 2024.0. oneAPI Deep Neural Network Library, oneAPI Math Kernel Library, and oneAPI DPC++/C++ Compiler are required, the other components are optional.
``` ```
### Install BigDL-LLM From PyPI ### Install BigDL-LLM From PyPI

4
python/llm/README.md
View file

@ -56,6 +56,7 @@ Over 20 models have been optimized/verified on `bigdl-llm`, including *LLaMA/LLa
| Baichuan2 | [link](example/CPU/HF-Transformers-AutoModels/Model/baichuan2) | [link](example/GPU/HF-Transformers-AutoModels/Model/baichuan2) | | Baichuan2 | [link](example/CPU/HF-Transformers-AutoModels/Model/baichuan2) | [link](example/GPU/HF-Transformers-AutoModels/Model/baichuan2) |
| InternLM | [link](example/CPU/HF-Transformers-AutoModels/Model/internlm) | [link](example/GPU/HF-Transformers-AutoModels/Model/internlm) | | InternLM | [link](example/CPU/HF-Transformers-AutoModels/Model/internlm) | [link](example/GPU/HF-Transformers-AutoModels/Model/internlm) |
| Qwen | [link](example/CPU/HF-Transformers-AutoModels/Model/qwen) | [link](example/GPU/HF-Transformers-AutoModels/Model/qwen) | | Qwen | [link](example/CPU/HF-Transformers-AutoModels/Model/qwen) | [link](example/GPU/HF-Transformers-AutoModels/Model/qwen) |
| Qwen1.5 | [link](example/CPU/HF-Transformers-AutoModels/Model/qwen1.5) | [link](example/GPU/HF-Transformers-AutoModels/Model/qwen1.5) |
| Qwen-VL | [link](example/CPU/HF-Transformers-AutoModels/Model/qwen-vl) | [link](example/GPU/HF-Transformers-AutoModels/Model/qwen-vl) | | Qwen-VL | [link](example/CPU/HF-Transformers-AutoModels/Model/qwen-vl) | [link](example/GPU/HF-Transformers-AutoModels/Model/qwen-vl) |
| Aquila | [link](example/CPU/HF-Transformers-AutoModels/Model/aquila) | [link](example/GPU/HF-Transformers-AutoModels/Model/aquila) | | Aquila | [link](example/CPU/HF-Transformers-AutoModels/Model/aquila) | [link](example/GPU/HF-Transformers-AutoModels/Model/aquila) |
| Aquila2 | [link](example/CPU/HF-Transformers-AutoModels/Model/aquila2) | [link](example/GPU/HF-Transformers-AutoModels/Model/aquila2) | | Aquila2 | [link](example/CPU/HF-Transformers-AutoModels/Model/aquila2) | [link](example/GPU/HF-Transformers-AutoModels/Model/aquila2) |
@ -63,7 +64,6 @@ Over 20 models have been optimized/verified on `bigdl-llm`, including *LLaMA/LLa
| Whisper | [link](example/CPU/HF-Transformers-AutoModels/Model/whisper) | [link](example/GPU/HF-Transformers-AutoModels/Model/whisper) | | Whisper | [link](example/CPU/HF-Transformers-AutoModels/Model/whisper) | [link](example/GPU/HF-Transformers-AutoModels/Model/whisper) |
| Phi-1_5 | [link](example/CPU/HF-Transformers-AutoModels/Model/phi-1_5) | [link](example/GPU/HF-Transformers-AutoModels/Model/phi-1_5) | | Phi-1_5 | [link](example/CPU/HF-Transformers-AutoModels/Model/phi-1_5) | [link](example/GPU/HF-Transformers-AutoModels/Model/phi-1_5) |
| Flan-t5 | [link](example/CPU/HF-Transformers-AutoModels/Model/flan-t5) | [link](example/GPU/HF-Transformers-AutoModels/Model/flan-t5) | | Flan-t5 | [link](example/CPU/HF-Transformers-AutoModels/Model/flan-t5) | [link](example/GPU/HF-Transformers-AutoModels/Model/flan-t5) |
| Qwen-VL | [link](example/CPU/HF-Transformers-AutoModels/Model/qwen-vl) | |
| LLaVA | [link](example/CPU/PyTorch-Models/Model/llava) | [link](example/GPU/PyTorch-Models/Model/llava) | | LLaVA | [link](example/CPU/PyTorch-Models/Model/llava) | [link](example/GPU/PyTorch-Models/Model/llava) |
| CodeLlama | [link](example/CPU/HF-Transformers-AutoModels/Model/codellama) | [link](example/GPU/HF-Transformers-AutoModels/Model/codellama) | | CodeLlama | [link](example/CPU/HF-Transformers-AutoModels/Model/codellama) | [link](example/GPU/HF-Transformers-AutoModels/Model/codellama) |
| Skywork | [link](example/CPU/HF-Transformers-AutoModels/Model/skywork) | | | Skywork | [link](example/CPU/HF-Transformers-AutoModels/Model/skywork) | |
@ -82,8 +82,6 @@ Over 20 models have been optimized/verified on `bigdl-llm`, including *LLaMA/LLa
| Bark | [link](example/CPU/PyTorch-Models/Model/bark) | [link](example/GPU/PyTorch-Models/Model/bark) | | Bark | [link](example/CPU/PyTorch-Models/Model/bark) | [link](example/GPU/PyTorch-Models/Model/bark) |
| SpeechT5 | | [link](example/GPU/PyTorch-Models/Model/speech-t5) | | SpeechT5 | | [link](example/GPU/PyTorch-Models/Model/speech-t5) |
| Ziya-Coding-34B-v1.0 | [link](example/CPU/HF-Transformers-AutoModels/Model/ziya) | | | Ziya-Coding-34B-v1.0 | [link](example/CPU/HF-Transformers-AutoModels/Model/ziya) | |
| Qwen1.5 | [link](example/CPU/HF-Transformers-AutoModels/Model/qwen1.5) | [link](example/GPU/HF-Transformers-AutoModels/Model/qwen1.5) |
### Working with `bigdl-llm` ### Working with `bigdl-llm`