Skip to content

[TRTLLM-5366][feat]Add support for sm121 #5524

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
schetlur-nv merged 11 commits into from
Jul 8, 2025
Merged

[TRTLLM-5366][feat]Add support for sm121 #5524

schetlur-nv merged 11 commits into from
Jul 8, 2025

Conversation

@pamelap-nvidia
Copy link
Collaborator

@pamelap-nvidia pamelap-nvidia commented Jun 26, 2025 •
edited
Loading

Following SM120 logic in most places.
@pamelap-nvidia pamelap-nvidia self-assigned this Jun 26, 2025
@pamelap-nvidia
Copy link
Collaborator Author

pamelap-nvidia commented Jun 27, 2025

/bot run
@pamelap-nvidia
Copy link
Collaborator Author

pamelap-nvidia commented Jun 27, 2025

/bot run
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 27, 2025

PR_Github #10096 [ run ] triggered by Bot
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 27, 2025

PR_Github #10096 [ run ] completed with state FAILURE
@pamelap-nvidia pamelap-nvidia force-pushed the digits branch 2 times, most recently from b73b668 to ff1952e Compare June 27, 2025 15:17
@pamelap-nvidia
Copy link
Collaborator Author

pamelap-nvidia commented Jun 27, 2025

/bot run
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 27, 2025

PR_Github #10165 [ run ] triggered by Bot
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 27, 2025

PR_Github #10165 [ run ] completed with state FAILURE
@pamelap-nvidia
Copy link
Collaborator Author

pamelap-nvidia commented Jun 27, 2025

/bot run
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 27, 2025

PR_Github #10179 [ ] completed with state FAILURE
@pamelap-nvidia
Copy link
Collaborator Author

pamelap-nvidia commented Jun 29, 2025

/bot run
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 29, 2025

PR_Github #10245 [ run ] triggered by Bot
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 29, 2025

PR_Github #10245 [ run ] completed with state FAILURE
@pamelap-nvidia
Copy link
Collaborator Author

pamelap-nvidia commented Jun 30, 2025

/bot run
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 30, 2025

PR_Github #10251 [ run ] triggered by Bot
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 30, 2025

PR_Github #10251 [ run ] completed with state FAILURE
@pamelap-nvidia
Copy link
Collaborator Author

pamelap-nvidia commented Jun 30, 2025

/bot run
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 30, 2025

PR_Github #10253 [ run ] triggered by Bot
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 30, 2025

PR_Github #10253 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7578 completed with status: 'FAILURE'
@pamelap-nvidia
Copy link
Collaborator Author

pamelap-nvidia commented Jun 30, 2025

/bot run --disable-fail-fast
@pamelap-nvidia
Squashed.
78de852 
121 changes. Allow building with 121a-real. Add testlist for digts and fix the memory issue of nvidia-smi memory is NA on digits Signed-off-by: Pamela Peng <179191831+pamelap-nvidia@users.noreply.github.com>
@pamelap-nvidia
unwaive fp4 tests
d26cf9b 
Signed-off-by: Pamela Peng <179191831+pamelap-nvidia@users.noreply.github.com>
@pamelap-nvidia
Merge branch 'main' into digits
5c35792 
Signed-off-by: Pamela Peng <179191831+pamelap-nvidia@users.noreply.github.com>
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jul 3, 2025

PR_Github #10666 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7890 (Partly Tested) completed with status: 'FAILURE'
@chzblych
Copy link
Collaborator

chzblych commented Jul 3, 2025

/bot run --extra-stage "RTXPro6000-PyTorch-Post-Merge-1"
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jul 3, 2025

PR_Github #10752 [ run ] triggered by Bot
chzblych
chzblych reviewed Jul 3, 2025
View reviewed changes
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jul 3, 2025

PR_Github #10752 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7943 completed with status: 'FAILURE'
@chzblych
Copy link
Collaborator

chzblych commented Jul 3, 2025

/bot run --extra-stage "RTXPro6000-PyTorch-Post-Merge-1" --disable-fail-fast
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jul 3, 2025

PR_Github #10789 [ run ] triggered by Bot
@chzblych chzblych enabled auto-merge (squash) July 3, 2025 10:11
@chzblych chzblych disabled auto-merge July 3, 2025 10:11
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jul 3, 2025

PR_Github #10789 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7969 completed with status: 'FAILURE'
@chzblych
Copy link
Collaborator

chzblych commented Jul 4, 2025

/bot run --extra-stage "RTXPro6000-PyTorch-Post-Merge-1" --disable-fail-fast
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jul 4, 2025

PR_Github #10913 [ run ] triggered by Bot
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jul 4, 2025

PR_Github #10913 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8066 completed with status: 'FAILURE'
@pamelap-nvidia
Merge branch 'main' into digits
2b6db58 
Signed-off-by: Pamela Peng <179191831+pamelap-nvidia@users.noreply.github.com>
@pamelap-nvidia
Copy link
Collaborator Author

pamelap-nvidia commented Jul 7, 2025

/bot run --extra-stage "RTXPro6000-PyTorch-Post-Merge-1" --disable-fail-fast
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jul 7, 2025

PR_Github #11164 [ run ] triggered by Bot
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jul 8, 2025

PR_Github #11164 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8257 completed with status: 'FAILURE'
@pamelap-nvidia
Copy link
Collaborator Author

pamelap-nvidia commented Jul 8, 2025

/bot run --stage-list "A30-CPP-3"
1 similar comment
@pamelap-nvidia
Copy link
Collaborator Author

pamelap-nvidia commented Jul 8, 2025

/bot run --stage-list "A30-CPP-3"
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jul 8, 2025

PR_Github #11323 [ run ] triggered by Bot
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jul 8, 2025

PR_Github #11323 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8376 (Partly Tested) completed with status: 'SUCCESS'
@schetlur-nv schetlur-nv merged commit da8c737 into NVIDIA:main Jul 8, 2025
2 checks passed
@SimengLiu-nv SimengLiu-nv mentioned this pull request Jul 8, 2025
Open
zhou-yuxin pushed a commit to zhou-yuxin/TensorRT-LLM that referenced this pull request Jul 15, 2025
@pamelap-nvidia @zhou-yuxin
[TRTLLM-5366][feat]Add support for sm121 (NVIDIA#5524)
77faa61 
Signed-off-by: Pamela Peng <179191831+pamelap-nvidia@users.noreply.github.com> Co-authored-by: Yanchao Lu <yanchaol@nvidia.com> Initial CI run failed a single step A30-CPP-3 due to timeout. Rerunning that step succeeded. Signed-off-by: Yuxin <yuxinz@nvidia.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

5 participants

@pamelap-nvidia @tensorrt-cicd @farazkh80 @chzblych @schetlur-nv