Skip to content

Conversation

@n1ck-guo
Copy link
Contributor

@n1ck-guo n1ck-guo commented Sep 8, 2025

No description provided.

Signed-off-by: n1ck-guo <heng.guo@intel.com>
Signed-off-by: n1ck-guo <heng.guo@intel.com>
Copy link
Contributor

@wenhuach21 wenhuach21 left a comment

Choose a reason for hiding this comment

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

fix device_map=dict

n1ck-guo and others added 3 commits September 8, 2025 21:43
Signed-off-by: n1ck-guo <heng.guo@intel.com>
Signed-off-by: n1ck-guo <heng.guo@intel.com>
@wenhuach21 wenhuach21 changed the title AutoRoundMLLM supports scheme AutoRoundMLLM supports scheme and fix device_map=dict regression Sep 9, 2025
import habana_frameworks.torch.core as htcore # pylint: disable=E0401
import habana_frameworks.torch.hpu as hthpu # pylint: disable=E0401]

def _set_device(self, device_map):
Copy link
Contributor

Choose a reason for hiding this comment

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

add type

tmp_device = detect_device(val)
tmp_device = tmp_device.split(":")[0]
tmp_devices.append(tmp_device)
tmp_devices = list(set(tmp_devices))
Copy link
Contributor

@wenhuach21 wenhuach21 Sep 9, 2025

Choose a reason for hiding this comment

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

set could not keep the order, which may increase debugging effort in the future.
How about using this one
https://github.com/intel/auto-round/blob/main/auto_round/autoround.py#L789

@wenhuach21 wenhuach21 merged commit 78fce45 into main Sep 9, 2025
8 checks passed
@wenhuach21 wenhuach21 deleted the hengguo/vlm_scheme branch September 9, 2025 04:48
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants