Add mark_step for encoder layers #650
Closed
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
yisonzhu
requested review from
kzawora-intel,
madamczykhabana,
michalkuligowski and
mgawarkiewicz
as code owners
michalkuligowski
force-pushed
the
dev/mark_step_for_encoder
branch
from
c2f7554 to
5efc637
Compare
michalkuligowski
requested changes
Jan 7, 2025
| @@ -135,7 +135,7 @@ def flatten(in_list): | |||
| return list(itertools.chain(*in_list)) | |||
|
|
|||
|
|
|||
| def get_decoder_layer_suffix(model_type): | |||
| def get_target_layer_suffix(model_type) -> list[str]: | |||
There was a problem hiding this comment.
Please change to something like "get_target_layer_suffix_list" to reflect return type
| n=1, | ||
| counter=None): | ||
| def modify_model_layers(module: torch.nn.Module, | ||
| suffix: list[str], |
There was a problem hiding this comment.
Please change to something like "suffix_list" to reflect the underlying type
|
Hi @michalkuligowski, thanks for your review but I need to create a new PR #669 to address your comments. Can you help close this one and take a look at the new one? |
michalkuligowski
pushed a commit
that referenced
this pull request
Jan 8, 2025
This is a updated version from #650. Coupled with [Use FusedSDPA for MllamaVisionSdpaAttention #620], these two issues arising when running llama3.2 vision model can be resolved: GC fail when batchsize>1 on Gaudi3. Increased device memory consumption with Torch 2.5 compared to Torch 2.4. --------- Signed-off-by: yan ma <[email protected]> Co-authored-by: yisonzhu <[email protected]>
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Outdated suggestions cannot be applied.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.
Coupled with [Use FusedSDPA for MllamaVisionSdpaAttention #620], these two issues arising when running llama3.2 vision model can be resolved: