fix: multiple bug fixes: #70
Merged
Conversation
This file contains hidden or 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
1. config_quant_smooth_lays() always resets qcfg["qskip_lay_name"] and loses user-defined info, 2. act_scales didn't check existing files 3. get_mod_act_scales() and cache_block0() didn't check and cache and use position_embeddings 4. act_scale is usually saved in higher prec but QLinear didn't preserve dtype after scaling 5. try to enable device_map="auto" for easier large model inference Signed-off-by: cliu-us <[email protected]>
chichun-charlie-liu
requested review from
andrea-fasoli,
kcirred,
nwang-ibm and
tharapalanivel
as code owners
Signed-off-by: cliu-us <[email protected]>
chichun-charlie-liu
merged commit 136c12f
into
foundation-model-stack:main
12 checks passed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Description of the change
Related issue number
How to verify the PR
Was the PR tested