Skip to content

feat: Mistral-Large-2 support in the Pytorch workflow #3845

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 8 commits into from
Apr 30, 2025
Merged

feat: Mistral-Large-2 support in the Pytorch workflow #3845

merged 8 commits into from
Apr 30, 2025

Conversation

hypdeb
Copy link
Collaborator

@hypdeb hypdeb commented Apr 24, 2025

  • Separate modelling logic for Mistral as its configuration is different than Llama models

@hypdeb hypdeb mentioned this pull request Apr 24, 2025
Closed
@hypdeb hypdeb requested a review from QiJune April 24, 2025 18:08
@hypdeb
Copy link
Collaborator Author

hypdeb commented Apr 24, 2025

/bot run

@hypdeb
Copy link
Collaborator Author

hypdeb commented Apr 24, 2025

@QiJune oh I see there's an issue with Nemotron in my changeset. Let me fix it.

@hypdeb hypdeb force-pushed the mistral_pytorch_support branch from e9cc635 to 04acf4e Compare April 24, 2025 18:14
@hypdeb
Copy link
Collaborator Author

hypdeb commented Apr 24, 2025

/bot kill

@hypdeb
Copy link
Collaborator Author

hypdeb commented Apr 24, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3319 [ run ] triggered by Bot

@hypdeb hypdeb self-assigned this Apr 24, 2025
@hypdeb hypdeb added new model Request to add a new model LLM API/Workflow High-level LLM Python API & tools (e.g., trtllm-llmapi-launch) for TRTLLM inference/workflows. labels Apr 24, 2025
@tensorrt-cicd
Copy link
Collaborator

PR_Github #3321 [ kill ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3322 [ ] completed with state ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3319 [ run ] completed with state ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3321 [ kill ] completed with state SUCCESS
Successfully killed previous jobs for commit 04acf4e

@hypdeb
Copy link
Collaborator Author

hypdeb commented Apr 24, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3324 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3324 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #2318 completed with status: 'FAILURE'

@hypdeb
Copy link
Collaborator Author

hypdeb commented Apr 25, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3365 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3365 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #2352 completed with status: 'FAILURE'

@hypdeb
Copy link
Collaborator Author

hypdeb commented Apr 25, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3417 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3417 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #2399 completed with status: 'SUCCESS'

@hypdeb
Copy link
Collaborator Author

hypdeb commented Apr 26, 2025

/bot reuse-pipeline

@hypdeb
Copy link
Collaborator Author

hypdeb commented Apr 26, 2025

@QiJune pipeline is green. Could you please have another look?

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3447 [ reuse-pipeline ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3447 [ reuse-pipeline ] completed with state SUCCESS
Reusing PR_Github #3417 for commit 6f46867

@hypdeb
Copy link
Collaborator Author

hypdeb commented Apr 28, 2025

/bot reuse-pipeline

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3567 [ reuse-pipeline ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3567 [ reuse-pipeline ] completed with state SUCCESS
Reusing PR_Github #3417 for commit 2af0ccf

@hypdeb hypdeb force-pushed the mistral_pytorch_support branch from 9282fd4 to 56c4375 Compare April 30, 2025 06:29
@hypdeb
Copy link
Collaborator Author

hypdeb commented Apr 30, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3807 [ run ] triggered by Bot

QiJune
QiJune approved these changes Apr 30, 2025
View reviewed changes
Copy link
Collaborator

@QiJune QiJune left a comment

Choose a reason for hiding this comment

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

LGTM

@hypdeb hypdeb enabled auto-merge (squash) April 30, 2025 07:32
@tensorrt-cicd
Copy link
Collaborator

PR_Github #3807 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #2693 completed with status: 'FAILURE'

@hypdeb
Copy link
Collaborator Author

hypdeb commented Apr 30, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3814 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3814 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #2698 completed with status: 'FAILURE'

@hypdeb
Copy link
Collaborator Author

hypdeb commented Apr 30, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3839 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #3839 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #2719 completed with status: 'SUCCESS'

@hypdeb hypdeb merged commit 8367057 into NVIDIA:main Apr 30, 2025
3 checks passed
@hypdeb hypdeb deleted the mistral_pytorch_support branch April 30, 2025 12:40
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@QiJune QiJune QiJune approved these changes

Assignees

@hypdeb hypdeb

Labels
LLM API/Workflow High-level LLM Python API & tools (e.g., trtllm-llmapi-launch) for TRTLLM inference/workflows. new model Request to add a new model
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@hypdeb @tensorrt-cicd @QiJune