Skip to content

feat: trtllm-gen fp4 GEMM for pytorch workflow #3423

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 4 commits into from
Apr 10, 2025
Merged

feat: trtllm-gen fp4 GEMM for pytorch workflow #3423

merged 4 commits into from
Apr 10, 2025

Conversation

DomBrown
Copy link
Collaborator

@DomBrown DomBrown commented Apr 9, 2025

Adds FP4 GEMM from TRTLLM-Gen using the new exported interface.

@DomBrown DomBrown added the feature request New feature or request label Apr 9, 2025
@DomBrown DomBrown requested a review from nekorobov April 9, 2025 14:34
@DomBrown DomBrown self-assigned this Apr 9, 2025
@DomBrown
Copy link
Collaborator Author

DomBrown commented Apr 9, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #1627 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #1627 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #1217 completed with status: 'FAILURE'

@DomBrown
Copy link
Collaborator Author

DomBrown commented Apr 9, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #1634 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #1634 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #1221 completed with status: 'SUCCESS'

@DomBrown
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #1754 [ run ] triggered by Bot

@DomBrown
Copy link
Collaborator Author

/bot kill

@tensorrt-cicd
Copy link
Collaborator

PR_Github #1783 [ kill ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #1754 [ run ] completed with state ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #1783 [ kill ] completed with state SUCCESS
Successfully killed previous jobs for commit c893d8e

@DomBrown
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #1788 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #1788 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #1326 completed with status: 'SUCCESS'

DomBrown added 4 commits April 10, 2025 19:15
@DomBrown
feat: trtllm-gen fp4 GEMM
6d8cbda 
Signed-off-by: Dom Brown <[email protected]>
@DomBrown
Clean up
6ccf8b9 
Signed-off-by: Dom Brown <[email protected]>
@DomBrown
Remove incorrect header
9c0b7bf 
Signed-off-by: Dom Brown <[email protected]>
@DomBrown
Reviewer comment
75d77ce 
Signed-off-by: Dom Brown <[email protected]>
@DomBrown DomBrown force-pushed the feat_fp4_gemm_trtllmgen branch from c893d8e to 75d77ce Compare April 10, 2025 18:15
@DomBrown
Copy link
Collaborator Author

/bot reuse-pipeline

@DomBrown DomBrown enabled auto-merge (squash) April 10, 2025 18:17
@tensorrt-cicd
Copy link
Collaborator

PR_Github #1815 [ reuse-pipeline ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #1815 [ reuse-pipeline ] completed with state SUCCESS
Reusing PR_Github #1788 for commit 75d77ce

@DomBrown DomBrown merged commit a8310b0 into NVIDIA:main Apr 10, 2025
2 checks passed
Superjomn pushed a commit to Superjomn/TensorRT-LLM that referenced this pull request Apr 11, 2025
@DomBrown @Superjomn
feat: trtllm-gen fp4 GEMM for pytorch workflow (NVIDIA#3423)
adf9976 
* feat: trtllm-gen fp4 GEMM

Signed-off-by: Dom Brown <[email protected]>

* Clean up

Signed-off-by: Dom Brown <[email protected]>

* Remove incorrect header

Signed-off-by: Dom Brown <[email protected]>

* Reviewer comment

Signed-off-by: Dom Brown <[email protected]>

---------

Signed-off-by: Dom Brown <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@nekorobov nekorobov nekorobov approved these changes

Assignees

@DomBrown DomBrown

Labels
feature request New feature or request
Projects
None yet
Milestone
No milestone
Development

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