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

Support Windows ARL release (#12183)

Browse source 
* Support release for ARL

* Small fix

* Small fix to doc

* Temp for test

* Remove temp commit for test
This commit is contained in:
Yuwen Hu 2024-10-11 18:30:52 +08:00 committed by GitHub
parent f983f1a8f4
commit ddcdf47539
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 8 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
docs/mddocs/Overview/install_gpu.md
View file

@ -46,7 +46,7 @@ We recommend using [Miniforge](https://conda-forge.org/download/) to create a py
The easiest ways to install `ipex-llm` is the following commands.
- For **Intel Core™ Ultra Series 2 (a.k.a. Lunar Lake) with Intel Arc™ Graphics**:
- For **Intel Core™ Ultra Series 2 with Intel Arc™ Graphics (a.k.a. Lunar Lake)**:
Choose either US or CN website for `extra-index-url`:
@ -94,7 +94,7 @@ The easiest ways to install `ipex-llm` is the following commands.
If you encounter network issues when installing IPEX, you can also install IPEX-LLM dependencies for Intel XPU from source archives. First you need to download and install torch/torchvision/ipex from wheels listed below before installing `ipex-llm`.
- For **Intel Core™ Ultra Series 2 (a.k.a. Lunar Lake) with Intel Arc™ Graphics**:
- For **Intel Core™ Ultra Series 2 with Intel Arc™ Graphics (a.k.a. Lunar Lake)**:
Download the wheels on Windows system:

2
docs/mddocs/Quickstart/install_windows_gpu.md
View file

@ -47,7 +47,7 @@ conda activate llm
With the `llm` environment active, use `pip` to install `ipex-llm` for GPU:
- For **Intel Core™ Ultra Series 2 (a.k.a. Lunar Lake) with Intel Arc™ Graphics**:
- For **Intel Core™ Ultra Series 2 with Intel Arc™ Graphics (a.k.a. Lunar Lake)**:
Choose either US or CN website for `extra-index-url`:

10
python/llm/setup.py
View file

@ -276,11 +276,9 @@ def setup_package():
oneapi_2024_0_requires = ["dpcpp-cpp-rt==2024.0.2;platform_system=='Windows'",
"mkl-dpcpp==2024.0.0;platform_system=='Windows'",
"onednn==2024.0.0;platform_system=='Windows'"]
"mkl-dpcpp==2024.0.0;platform_system=='Windows'"]
oneapi_2024_2_requires = ["dpcpp-cpp-rt==2024.2.1;platform_system=='Windows'",
"mkl-dpcpp==2024.2.1;platform_system=='Windows'",
"onednn==2024.2.1;platform_system=='Windows'"]
"mkl-dpcpp==2024.2.1;platform_system=='Windows'"]
# Linux install with --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
xpu_21_requires = copy.deepcopy(all_requires)
for exclude_require in cpu_torch_version:
@ -304,7 +302,8 @@ def setup_package():
"intel-extension-for-pytorch==2.3.110+xpu",
"bigdl-core-xe-23==" + CORE_XE_VERSION,
"bigdl-core-xe-batch-23==" + CORE_XE_VERSION,
"bigdl-core-xe-addons-23==" + CORE_XE_VERSION]
"bigdl-core-xe-addons-23==" + CORE_XE_VERSION,
"onednn-devel==2024.1.1;platform_system=='Windows'"]
cpp_requires = ["bigdl-core-cpp==" + CORE_XE_VERSION,
"onednn-devel==2024.2.1;platform_system=='Windows'"]
@ -345,6 +344,7 @@ def setup_package():
"npu": npu_requires,
"xpu-2-1": xpu_21_requires,
"xpu-lnl": xpu_lnl_requires,
"xpu-arl": xpu_lnl_requires,
"serving": serving_requires,
"cpp": cpp_requires,
"llama-index": llama_index_requires}, # for internal usage when upstreaming for llama-index