Skip to content

[kernels] Update npu kernel repository and layer name #42275

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

Closed
wants to merge 3 commits into from
Closed

[kernels] Update npu kernel repository and layer name #42275

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a6dcc2c
Update NPU kernel repository and layer name
zheliuyu Nov 18, 2025
ee90e16
Merge branch 'huggingface:main' into main
zheliuyu Nov 19, 2025
27220ce
Update training mode for npu rmsnorm layer
zheliuyu Nov 19, 2025
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
6 changes: 3 additions & 3 deletions src/transformers/integrations/hub_kernels.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,9 +85,9 @@ def use_kernel_forward_from_hub(layer_name: str):
)
},
"npu": {
Mode.INFERENCE: LayerRepository(
repo_id="kernels-community/liger_kernels",
layer_name="LigerRMSNorm",
Mode.TRAINING: LayerRepository(
repo_id="kernels-ext-npu/rmsnorm",
layer_name="rmsnorm",
Comment on lines -88 to +90
Copy link
Member

@SunMarc SunMarc Nov 19, 2025

Choose a reason for hiding this comment

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

for inference should we still keep liger_kernels ?

Copy link
Contributor

@MekkCyber MekkCyber Nov 19, 2025

Choose a reason for hiding this comment

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

Also @zheliuyu, I have a few concerns about including kernels from other communities that may not yet be fully mature in the default mapping of Transformers, since it's code being run on users devices, and we need to keep control of what's being executed. I would kindly suggest using the KernelConfig directly and specifying the desired mapping there instead of using the default one for now. For example:

kernel_config = KernelConfig(kernel_mapping={"RMSNorm": "kernels-ext-npu/rmsnorm:rmsnorm"})
model = AutoModelForCausalLM.from_pretrained(
            "unsloth/Llama-3.2-1B-Instruct", use_kernels=True, device_map=torch_device, kernel_config=kernel_config
        )

Once the npu community is mature enough we can consider adding kernels to the default mapping directly.

Copy link
Contributor Author

@zheliuyu zheliuyu Nov 24, 2025

Choose a reason for hiding this comment

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

Thanks for your guidance.

)
},
},
Expand Down