Open
Conversation
Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
…e sorted Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
Signed-off-by: Mamta Singh <mamtsing@qti.qualcomm.com>
quic-mamta
requested review from
ochougul,
quic-amitraj,
quic-hemagnih and
quic-rishinr
as code owners
Signed-off-by: Mamta Singh <mamtsing@qti.qualcomm.com>
Signed-off-by: Mamta Singh <mamtsing@qti.qualcomm.com>
| enable_chunking = kwargs.get("enable_chunking", False) | ||
|
|
||
| # TODO: HACK handle better | ||
| if enable_mla := kwargs.get("enable_mla", False): |
Contributor
There was a problem hiding this comment.
why do we need this boolean in kwargs?
if model has MLA, it should just be enabled.
Contributor
There was a problem hiding this comment.
Because we can treat it as full KV model as well, this will allow us to skip the upprojection on the full CTX for each decode iteration.
We can get rid of this, once we have data about if FULL KV is better or MLA is better
Signed-off-by: Mamta Singh <mamtsing@qti.qualcomm.com>
quic-mamta
force-pushed
the
mla_fusion
branch
from
b8b3326 to
c16a0c7
Compare
Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
Signed-off-by: Mamta Singh <168400541+quic-mamta@users.noreply.github.com>
Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
The export hash needs to different for different mla absorption config-> this needs to be fixed.