actorder #16
Closed
actorder #16
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
bfineran
approved these changes
Jul 9, 2024
bfineran
previously approved these changes
Jul 10, 2024
bfineran
approved these changes
Jul 22, 2024
mgoin
approved these changes
Jul 22, 2024
bfineran
reviewed
Jul 26, 2024
|
Moved to #94 |
markmc
pushed a commit
to markmc/llm-compressor
that referenced
this pull request
Nov 13, 2024
* test forward (vllm-project#16) * test frozen (vllm-project#17) * test frozen * rename * lifecycle conftest (vllm-project#21) * test initalize (vllm-project#18) * test initalize * newline * parametrize weights and inp_act * remove dup * test lifecycle (vllm-project#19) * test lifecycle * comments * comments * add quantization test * Lifecycle/min max obs (vllm-project#20) * min max test * add minmax obs * test scale range and min_max update * rebase * rebase * fix * fix
# for free
to join this conversation on GitHub.
Already have an account?
# 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Outdated suggestions cannot be applied.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.
SUMMARY:
Activation rerodering - groups the weight matrix based on the diagonal of the Hessians.
Grouping similar values so "like-alike" values should provide better scale, zp for the selected groups.
TEST PLAN:
Tested model with actoder = True and False. With actorder should provide a drop of increase in accuracy