Skip to content

feat: Remove not used padding_idx in models #5385

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
Jun 25, 2025
Merged

feat: Remove not used padding_idx in models #5385

merged 4 commits into from
Jun 25, 2025

Conversation

@HuiGao-NV
Copy link
Collaborator

@HuiGao-NV HuiGao-NV commented Jun 20, 2025

Remove not used padding_idx in models

@HuiGao-NV HuiGao-NV requested a review from QiJune June 20, 2025 12:28
@HuiGao-NV HuiGao-NV requested a review from a team as a code owner June 20, 2025 12:28
@HuiGao-NV HuiGao-NV requested a review from lfr-0531 June 20, 2025 12:28
@HuiGao-NV
Copy link
Collaborator Author

HuiGao-NV commented Jun 20, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 20, 2025

PR_Github #9557 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 20, 2025

PR_Github #9557 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7016 completed with status: 'FAILURE'

@HuiGao-NV
Copy link
Collaborator Author

HuiGao-NV commented Jun 20, 2025

/bot run --stage-list="DGX_H100-4_GPUs-PyTorch-DeepSeek-1,DGX_H100-4_GPUs-PyTorch-DeepSeek-2"

@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 20, 2025

PR_Github #9564 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 21, 2025

PR_Github #9564 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7023 (Partly Tested) completed with status: 'FAILURE'

QiJune
QiJune approved these changes Jun 24, 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

@HuiGao-NV
Copy link
Collaborator Author

HuiGao-NV commented Jun 24, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 24, 2025

PR_Github #9688 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 24, 2025

PR_Github #9688 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7123 completed with status: 'FAILURE'

@HuiGao-NV
Copy link
Collaborator Author

HuiGao-NV commented Jun 24, 2025

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 24, 2025

PR_Github #9766 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 25, 2025

PR_Github #9766 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7200 completed with status: 'FAILURE'

@HuiGao-NV
Copy link
Collaborator Author

HuiGao-NV commented Jun 25, 2025 •
edited
Loading

The failed case has been skipped.
unittest/B200_PCIe-PyTorch-1/unittests/_torch/thop/test_moe.py::test_moe_fp8[autotune-512-512-expert_info3-16]

if use_autotune:
    pytest.skip("https://nvbugs/5356427")

Need to rebase and rerun test.

@HuiGao-NV
Copy link
Collaborator Author

HuiGao-NV commented Jun 25, 2025

/bot run --disable-fail-fast --stage-list="B200_PCIe-PyTorch-1,DGX_H100-4_GPUs-CPP-1,DGX_H100-4_GPUs-PyTorch-DeepSeek-1,DGX_H100-4_GPUs-PyTorch-DeepSeek-2,DGX_H100-4_GPUs-PyTorch-Others-1"

@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 25, 2025

PR_Github #9797 [ run ] triggered by Bot

@HuiGao-NV HuiGao-NV enabled auto-merge (squash) June 25, 2025 07:28
@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 25, 2025

PR_Github #9797 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7226 (Partly Tested) completed with status: 'SUCCESS'

@HuiGao-NV
Copy link
Collaborator Author

HuiGao-NV commented Jun 25, 2025

/bot skip --comment="skip for rebase"

@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 25, 2025

PR_Github #9853 [ skip ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

tensorrt-cicd commented Jun 25, 2025

PR_Github #9853 [ skip ] completed with state SUCCESS
Skipping testing for commit c9efd07

@HuiGao-NV HuiGao-NV merged commit b3a4c1f into NVIDIA:main Jun 25, 2025
3 checks passed
@HuiGao-NV HuiGao-NV deleted the remove_pad_idx branch June 25, 2025 13:29
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 9, 2025
@HuiGao-NV @dominicshanshan
feat: Remove not used padding_idx in models (NVIDIA#5385)
4408534 
Signed-off-by: Hui Gao <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 10, 2025
@HuiGao-NV @dominicshanshan
feat: Remove not used padding_idx in models (NVIDIA#5385)
af34ae7 
Signed-off-by: Hui Gao <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 10, 2025
@HuiGao-NV @dominicshanshan
feat: Remove not used padding_idx in models (NVIDIA#5385)
bc277a9 
Signed-off-by: Hui Gao <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 10, 2025
@HuiGao-NV @dominicshanshan
feat: Remove not used padding_idx in models (NVIDIA#5385)
138a669 
Signed-off-by: Hui Gao <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 10, 2025
@HuiGao-NV @dominicshanshan
feat: Remove not used padding_idx in models (NVIDIA#5385)
cc0e4ec 
Signed-off-by: Hui Gao <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 11, 2025
@HuiGao-NV @dominicshanshan
feat: Remove not used padding_idx in models (NVIDIA#5385)
d0f4ef8 
Signed-off-by: Hui Gao <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 11, 2025
@HuiGao-NV @dominicshanshan
feat: Remove not used padding_idx in models (NVIDIA#5385)
a8c5a4d 
Signed-off-by: Hui Gao <[email protected]>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Jul 11, 2025
@HuiGao-NV @dominicshanshan
feat: Remove not used padding_idx in models (NVIDIA#5385)
1614d52 
Signed-off-by: Hui Gao <[email protected]>
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

@lfr-0531 lfr-0531 Awaiting requested review from lfr-0531 lfr-0531 was automatically assigned from NVIDIA/trt-llm-torch-devs

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@HuiGao-NV @tensorrt-cicd @QiJune