Skip to content

fix: custom llama #1012

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
thomasdhc merged 15 commits into from
Jan 6, 2026
Merged

fix: custom llama #1012

thomasdhc merged 15 commits into from
Jan 6, 2026
+102 −159

Conversation

@akoumpa
Copy link
Contributor

@akoumpa akoumpa commented Jan 5, 2026 •
edited
Loading

What does this PR do ?

  • deprecate build_llama_model
  • fix model registration in AM custom registry

Changelog

  • Add specific line by line info of high level changes in this PR.

Before your PR is "Ready for review"

Pre checks:

  • Make sure you read and followed Contributor guidelines
  • Did you write any new necessary tests?
  • Did you add or update any necessary documentation?

If you haven't finished some of the above items you can still open "Draft" PR.

Additional Information

  • Related to # (issue)

akoumpa added 5 commits January 5, 2026 05:17
@akoumpa
del __all__ to make it surface in registyr
0f2d028 
Signed-off-by: Alexandros Koumparoulis <[email protected]>
@akoumpa
remnove build_llama_model
49f121f 
Signed-off-by: Alexandros Koumparoulis <[email protected]>
@akoumpa
remove build_llama_model mentions
f330ef4 
Signed-off-by: Alexandros Koumparoulis <[email protected]>
@akoumpa
remove build_llama_model
d2d0410 
Signed-off-by: Alexandros Koumparoulis <[email protected]>
@akoumpa
remove build_llama_mdoel
4f8c1e9 
Signed-off-by: Alexandros Koumparoulis <[email protected]>
@copy-pr-bot
Copy link

copy-pr-bot bot commented Jan 5, 2026

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

akoumpa added 4 commits January 5, 2026 08:05
@akoumpa
remove unused args
70928fe 
Signed-off-by: Alexandros Koumparoulis <[email protected]>
@akoumpa
propagate attn_implementation
e761815 
Signed-off-by: Alexandros Koumparoulis <[email protected]>
@akoumpa
propagate attn_implementation
d3d0f8f 
Signed-off-by: Alexandros Koumparoulis <[email protected]>
@akoumpa
fix
456cfc5 
Signed-off-by: Alexandros Koumparoulis <[email protected]>
@akoumpa
Copy link
Contributor Author

akoumpa commented Jan 5, 2026

/ok to test 456cfc5

@akoumpa
lint
aa3329e 
Signed-off-by: Alexandros Koumparoulis <[email protected]>
@akoumpa
Copy link
Contributor Author

akoumpa commented Jan 5, 2026

/ok to test aa3329e

@akoumpa
lint
dbb4ed6 
Signed-off-by: Alexandros Koumparoulis <[email protected]>
@akoumpa
Copy link
Contributor Author

akoumpa commented Jan 5, 2026

/ok to test dbb4ed6

@akoumpa akoumpa marked this pull request as ready for review January 6, 2026 16:09
HuiyingLi
HuiyingLi approved these changes Jan 6, 2026
View reviewed changes
Copy link
Contributor

@HuiyingLi HuiyingLi left a comment

Choose a reason for hiding this comment

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

LGTM

@thomasdhc thomasdhc merged commit b7031bb into main Jan 6, 2026
51 of 52 checks passed
@thomasdhc thomasdhc deleted the akoumparouli/fix_custom_llama branch January 6, 2026 18:36
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@HuiyingLi HuiyingLi HuiyingLi approved these changes

@adil-a adil-a Awaiting requested review from adil-a adil-a is a code owner

@hemildesai hemildesai Awaiting requested review from hemildesai hemildesai is a code owner

@ybabakhin ybabakhin Awaiting requested review from ybabakhin ybabakhin is a code owner

@shan-nvidia shan-nvidia Awaiting requested review from shan-nvidia shan-nvidia is a code owner

@rnyak rnyak Awaiting requested review from rnyak rnyak is a code owner

@oliverholworthy oliverholworthy Awaiting requested review from oliverholworthy oliverholworthy is a code owner

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@akoumpa @HuiyingLi @thomasdhc