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.

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

[WIP] AWQ initial implementation #92

Closed
wants to merge 1 commit into from
Closed

[WIP] AWQ initial implementation #92

wants to merge 1 commit into from

Conversation

rahul-tuli
Copy link
Collaborator

SUMMARY:
"please provide a brief summary"

TEST PLAN:
"please outline how the changes were tested"

@qingquansong
Copy link

Hey @rahul-tuli , any timeline about when AWQ will be shipped and merged? Thank you!

:param state: state to run AWQ on
:return: True on a successful run, False otherwise
"""
if self.end and self.end != -1:
Copy link
Collaborator

@kylesayrs kylesayrs Sep 15, 2024

Choose a reason for hiding this comment

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

Currently user can pass self.end == 0

Suggested change
if self.end and self.end != -1:
if not (self.end is None or self.end == -1):

balance_layers = mapping.balance_layers

activations = self.scales_[mapping.smooth_name].inps
module2inspect = smooth_layer
Copy link
Collaborator

Choose a reason for hiding this comment

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

Not sure why there are two variable names

w_mean = w_scale.mean(0)

# [STEP 2]: Compute per-channel mean of the input activation with chunking
# move inp to cpu to avoid memory leak
Copy link
Collaborator

Choose a reason for hiding this comment

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

What operation causes the memory leak? Should the tensor be moved back to gpu after?

@rahul-tuli
Copy link
Collaborator Author

Closing as all the individual pieces; are now broken down into separate stacked diffs in #181

@rahul-tuli rahul-tuli closed this Sep 18, 2024
markmc pushed a commit to markmc/llm-compressor that referenced this pull request Nov 13, 2024
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