Skip to content

feat: Add support for YARN in NemotronNAS models #4906

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
merged 5 commits into from
Jun 29, 2025
Merged

feat: Add support for YARN in NemotronNAS models #4906

merged 5 commits into from
Jun 29, 2025

Conversation

amirkl94
Copy link
Collaborator

@amirkl94 amirkl94 commented Jun 4, 2025

Support yarn in NemotronNAS models

Description

Add yarn positional embedding support in NemotronNAS

@amirkl94 amirkl94 requested a review from a team as a code owner June 4, 2025 08:41
@amirkl94 amirkl94 requested review from QiJune, hyukn and Naveassaf June 4, 2025 08:41
@Naveassaf
Copy link
Collaborator

/bot run

Naveassaf
Naveassaf approved these changes Jun 4, 2025
View reviewed changes
Copy link
Collaborator

@Naveassaf Naveassaf left a comment

Choose a reason for hiding this comment

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

LGTM. Please run manual testing as the required Mistral tokenizer lib is not public yet.

@tensorrt-cicd
Copy link
Collaborator

PR_Github #7532 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #7532 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #5464 completed with status: 'SUCCESS'

@amirkl94 amirkl94 requested a review from a team as a code owner June 19, 2025 14:22
@amirkl94
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9534 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9534 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #6996 completed with status: 'ABORTED'

@amirkl94
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9646 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9646 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #7091 completed with status: 'ABORTED'

@amirkl94 amirkl94 requested a review from tijyojwad June 24, 2025 07:08
@amirkl94 amirkl94 force-pushed the feature/support-yarn-nemotronnas branch from 2bc7a1f to 3790b00 Compare June 24, 2025 08:38
@amirkl94
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9665 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9665 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7107 completed with status: 'FAILURE'

@amirkl94
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9692 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9692 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7127 completed with status: 'FAILURE'

@amirkl94
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9712 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9712 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7147 completed with status: 'FAILURE'

@amirkl94
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9727 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9727 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7161 completed with status: 'FAILURE'

@amirkl94
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9826 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9826 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7251 completed with status: 'FAILURE'

@amirkl94 amirkl94 force-pushed the feature/support-yarn-nemotronnas branch from f5fa8ef to 541b22b Compare June 26, 2025 09:39
@amirkl94
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10023 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #10023 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7393 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

@Naveassaf Naveassaf merged commit de97799 into NVIDIA:main Jun 29, 2025
3 checks passed
ameynaik-hub pushed a commit to ameynaik-hub/TensorRT-LLM that referenced this pull request Jun 30, 2025
@amirkl94 @ameynaik-hub
feat: Add support for YARN in NemotronNAS models (NVIDIA#4906)
ae701b0 
Signed-off-by: Amir Klein <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 9, 2025
@amirkl94 @dominicshanshan
feat: Add support for YARN in NemotronNAS models (NVIDIA#4906)
9a769ed 
Signed-off-by: Amir Klein <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 10, 2025
@amirkl94 @dominicshanshan
feat: Add support for YARN in NemotronNAS models (NVIDIA#4906)
260307e 
Signed-off-by: Amir Klein <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 10, 2025
@amirkl94 @dominicshanshan
feat: Add support for YARN in NemotronNAS models (NVIDIA#4906)
33c8f81 
Signed-off-by: Amir Klein <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 10, 2025
@amirkl94 @dominicshanshan
feat: Add support for YARN in NemotronNAS models (NVIDIA#4906)
9379e5f 
Signed-off-by: Amir Klein <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 10, 2025
@amirkl94 @dominicshanshan
feat: Add support for YARN in NemotronNAS models (NVIDIA#4906)
3a504e0 
Signed-off-by: Amir Klein <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 11, 2025
@amirkl94 @dominicshanshan
feat: Add support for YARN in NemotronNAS models (NVIDIA#4906)
0a3bbb1 
Signed-off-by: Amir Klein <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 11, 2025
@amirkl94 @dominicshanshan
feat: Add support for YARN in NemotronNAS models (NVIDIA#4906)
59cb8b5 
Signed-off-by: Amir Klein <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 11, 2025
@amirkl94 @dominicshanshan
feat: Add support for YARN in NemotronNAS models (NVIDIA#4906)
a9ef247 
Signed-off-by: Amir Klein <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Naveassaf Naveassaf Naveassaf approved these changes

@liji-nv liji-nv liji-nv approved these changes

@QiJune QiJune Awaiting requested review from QiJune QiJune was automatically assigned from NVIDIA/trt-llm-torch-devs

@hyukn hyukn Awaiting requested review from hyukn hyukn was automatically assigned from NVIDIA/trt-llm-torch-devs

@tijyojwad tijyojwad Awaiting requested review from tijyojwad

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
@amirkl94 @Naveassaf @tensorrt-cicd @liji-nv