Skip to content

Fixed Granite_moe and added to CI#771

Merged
quic-akuruvil merged 6 commits intoquic:mainfrom
quic-akuruvil:fix
Feb 26, 2026
Merged

Fixed Granite_moe and added to CI#771
quic-akuruvil merged 6 commits intoquic:mainfrom
quic-akuruvil:fix

Conversation

@quic-akuruvil
Copy link
Contributor

@quic-akuruvil quic-akuruvil commented Feb 2, 2026

Granitemoe export issue fixed and added to CI.

@quic-rishinr
Copy link
Contributor

quic-rishinr commented Feb 4, 2026

@vbaddi please review the PR, CI is passing

"hpcai-tech/grok-1",
"Snowflake/Llama-3.1-SwiftKV-8B-Instruct",
"allenai/OLMo-2-0425-1B",
"ibm-granite/granite-3.1-1b-a400m-base",
Copy link
Contributor

Choose a reason for hiding this comment

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

please add dummy config in custom_tiny_model_configs.json as well.

@quic-akuruvil quic-akuruvil force-pushed the fix branch 2 times, most recently from be337a9 to 04a6c4d Compare February 20, 2026 07:22
@quic-akuruvil quic-akuruvil self-assigned this Feb 20, 2026
Ann Kuruvilla added 4 commits February 25, 2026 14:28
Signed-off-by: Ann <quic_akuruvil@quicinc.com>
Signed-off-by: Ann <quic_akuruvil@quicinc.com>
Signed-off-by: Ann <akuruvil@qti.qualcomm.com>
Signed-off-by: Ann <akuruvil@qti.qualcomm.com>
comp_ctx_lengths: Optional[torch.LongTensor] = None,
batch_index: Optional[torch.LongTensor] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
# labels: Optional[torch.LongTensor] = None,
Copy link
Contributor

Choose a reason for hiding this comment

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

please remove the commented lines

inputs_embeds = inputs_embeds * self.embedding_multiplier # main diff with Llama

# TODO (joao): remove this exception in v4.56 -- it exists for users that try to pass a legacy cache
# if not isinstance(past_key_values, (type(None), Cache)):
Copy link
Contributor

Choose a reason for hiding this comment

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

Do we need these? can we clean up?

Ann Kuruvilla added 2 commits February 26, 2026 04:22
Signed-off-by: Ann <akuruvil@qti.qualcomm.com>
Signed-off-by: Ann <akuruvil@qti.qualcomm.com>
@quic-akuruvil quic-akuruvil merged commit a6f2dd4 into quic:main Feb 26, 2026
4 checks passed
smedhe pushed a commit to smedhe/QEff_Sharvari that referenced this pull request Mar 8, 2026
Granitemoe export issue fixed and added to CI.

---------

Signed-off-by: Ann <akuruvil@qti.qualcomm.com>
Co-authored-by: Ann Kuruvilla <akuruvil@qti.qualcomm.com>
Signed-off-by: Sharvari Medhe <smedhe@qti.qualcomm.com>
smedhe pushed a commit to smedhe/QEff_Sharvari that referenced this pull request Mar 8, 2026
Granitemoe export issue fixed and added to CI.

---------

Signed-off-by: Ann <akuruvil@qti.qualcomm.com>
Co-authored-by: Ann Kuruvilla <akuruvil@qti.qualcomm.com>
Signed-off-by: Sharvari Medhe <smedhe@qti.qualcomm.com>

Signed-off-by: Sharvari Medhe <smedhe@qti.qualcomm.com>
quic-dhirajku pushed a commit to asmigosw/efficient-transformers that referenced this pull request Mar 13, 2026
Granitemoe export issue fixed and added to CI.

---------

Signed-off-by: Ann <akuruvil@qti.qualcomm.com>
Co-authored-by: Ann Kuruvilla <akuruvil@qti.qualcomm.com>
Signed-off-by: Dhiraj Kumar Sah <dhirajku@qti.qualcomm.com>
qcdipankar pushed a commit to qcdipankar/efficient-transformers that referenced this pull request Mar 17, 2026
Granitemoe export issue fixed and added to CI.

---------

Signed-off-by: Ann <akuruvil@qti.qualcomm.com>
Co-authored-by: Ann Kuruvilla <akuruvil@qti.qualcomm.com>
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.

2 participants