Fix Lora Rebase #290
Merged
Fix Lora Rebase #290
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| @@ -131,9 +132,9 @@ def convert_mapping( | |||
| if long_lora_context: | |||
| assert long_lora_offsets is not None | |||
| indices_list.append(long_lora_offsets) | |||
| indices = torch.tensor(indices_list, dtype=torch.long, device="cuda") | |||
| indices = torch.tensor(indices_list, dtype=torch.long, device=get_device()) | |||
There was a problem hiding this comment.
Suggested change
| indices = torch.tensor(indices_list, dtype=torch.long, device=get_device()) | |
| device = 'hpu' if current_platform.is_hpu() else 'cuda' | |
| indices = torch.tensor(indices_list, dtype=torch.long, device=device) |
Then use device instead of get_device() in the remainder of the file. For getting current_platform, add from vllm.platforms import current_platform at the top of the file.
There was a problem hiding this comment.
We are using get_device; to localize this if condition; as get_device is used in many places in lora/models.py, lora/punica.py. This way the code looks clean
hlahkar
force-pushed
the
dev/hlahkar/lora_rebase
branch
3 times, most recently
from
9d43b43
to
2a7e513
Compare
vivekgoe
requested changes
Sep 19, 2024
hlahkar
force-pushed
the
dev/hlahkar/lora_rebase
branch
from
2a7e513
to
b6a2d2a
Compare
vivekgoe
added
habana
|
@michalkuligowski I have changed label from Intel to Habana. Both myself & Himangshu are from Habana team :-) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes Lora Related issues in vllm Rebase