Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Support PyTorch 2.6 with Arrow Lake-H AOT on Windows #12967

Merged
merged 1 commit into from
Mar 13, 2025
+17 −1
Merged

Support PyTorch 2.6 with Arrow Lake-H AOT on Windows #12967

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 17 additions & 1 deletion python/llm/setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -312,7 +312,6 @@ def setup_package():
"onednn-devel==2024.1.1;platform_system=='Windows'",
"onednn==2024.1.1;platform_system=='Windows'"]

# Add for testing purposes for now
xpu_26_requires = copy.deepcopy(all_requires)
for exclude_require in cpu_torch_version:
xpu_26_requires.remove(exclude_require)
Expand All @@ -323,6 +322,22 @@ def setup_package():
"onednn-devel==2025.0.1",
"onednn==2025.0.1",
"dpcpp-cpp-rt==2025.0.2"]

# Add for testing purposes for now, for Arrow Lake-H with AOT on Windows
# Linux keeps the same as xpu_2.6
xpu_26_arl_requires = copy.deepcopy(all_requires)
for exclude_require in cpu_torch_version:
xpu_26_arl_requires.remove(exclude_require)
xpu_26_arl_requires += ["torch==2.6.0.post0+xpu;platform_system=='Windows'",
"torchvision==0.21.0.post0+xpu;platform_system=='Windows'",
"torchaudio==2.6.0.post0+xpu;platform_system=='Windows'",
"torch==2.6.0+xpu;platform_system=='Linux'",
"torchvision==0.21.0+xpu;platform_system=='Linux'",
"torchaudio==2.6.0+xpu;platform_system=='Linux'",
"bigdl-core-xe-all==" + CORE_XE_VERSION,
"onednn-devel==2025.0.1",
"onednn==2025.0.1",
"dpcpp-cpp-rt==2025.0.2"]

cpp_requires = ["bigdl-core-cpp==" + CORE_XE_VERSION,
"onednn-devel==2025.0.1;platform_system=='Windows'",
Expand Down Expand Up @@ -370,6 +385,7 @@ def setup_package():
"xpu-arl": xpu_lnl_requires,
"xpu-arc": xpu_lnl_requires,
"xpu-2-6": xpu_26_requires,
"xpu-2-6-arl": xpu_26_arl_requires,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

what's the difference between "xpu-arl" and "xpu-2-6-arl"?

Copy link
Contributor Author

@Oscilloscope98 Oscilloscope98 Mar 14, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

xpu_arl is previously added for ARL support with PyTorch 2.3.
xpu_2.6_arl is for PyTorch 2.6 + ARL-H AOT.

"serving": serving_requires,
"cpp": cpp_requires,
"llama-index": llama_index_requires}, # for internal usage when upstreaming for llama-index
Expand Down