Skip to content

[test] add nvfp4 DeepSeek-V3-Lite-mtp tests #5125

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 3 commits into from
Jun 19, 2025
Merged

[test] add nvfp4 DeepSeek-V3-Lite-mtp tests #5125

merged 3 commits into from
Jun 19, 2025

Conversation

lfr-0531
Copy link
Collaborator

Description

We already added a new nvfp4 DeepSeek-V3-Lite checkpoint with MTP weights to f"{llm_models_root()}/DeepSeek-V3-Lite/nvfp4_moe_only_mtp". In this PR, add nvfp4 DeepSeek-V3-Lite-mtp tests to both TestDeepSeekV3Lite::test_nvfp4 and TestDeepSeekV3Lite::test_nvfp4_4gpus.

@lfr-0531 lfr-0531 requested a review from hlu1 June 11, 2025 09:12
@lfr-0531 lfr-0531 force-pushed the user/fanrongl/add_nvfp4_mtp_tests branch 2 times, most recently from 538f0ae to 0519a31 Compare June 12, 2025 09:12
@lfr-0531
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #8654 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #8654 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #6277 completed with status: 'FAILURE'

@lfr-0531 lfr-0531 force-pushed the user/fanrongl/add_nvfp4_mtp_tests branch from 0519a31 to 5202429 Compare June 12, 2025 14:30
@lfr-0531
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #8694 [ run ] triggered by Bot

hlu1
hlu1 approved these changes Jun 12, 2025
View reviewed changes
@tensorrt-cicd
Copy link
Collaborator

PR_Github #8694 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #6301 completed with status: 'FAILURE'

@lfr-0531 lfr-0531 force-pushed the user/fanrongl/add_nvfp4_mtp_tests branch from 5202429 to e20cecd Compare June 13, 2025 04:31
@lfr-0531
Copy link
Collaborator Author

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #8736 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #8736 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #6339 completed with status: 'FAILURE'

@lfr-0531 lfr-0531 force-pushed the user/fanrongl/add_nvfp4_mtp_tests branch from e20cecd to 4bb0839 Compare June 15, 2025 09:23
@lfr-0531
Copy link
Collaborator Author

/bot run --disable-fail-fast

@lfr-0531 lfr-0531 force-pushed the user/fanrongl/add_nvfp4_mtp_tests branch from 4bb0839 to ba21d17 Compare June 15, 2025 15:16
@lfr-0531
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #8937 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #8937 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #6519 completed with status: 'FAILURE'

@lfr-0531 lfr-0531 force-pushed the user/fanrongl/add_nvfp4_mtp_tests branch from ba21d17 to ac680f8 Compare June 16, 2025 09:38
@lfr-0531
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9013 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9013 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #6583 completed with status: 'FAILURE'

@lfr-0531 lfr-0531 force-pushed the user/fanrongl/add_nvfp4_mtp_tests branch from ac680f8 to 0e39e98 Compare June 17, 2025 02:13
@lfr-0531
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9091 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9091 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #6653 completed with status: 'FAILURE'

@lfr-0531 lfr-0531 force-pushed the user/fanrongl/add_nvfp4_mtp_tests branch from f367c03 to 0fc68ca Compare June 17, 2025 05:16
@lfr-0531
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9137 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9137 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #6690 completed with status: 'FAILURE'

@lfr-0531 lfr-0531 force-pushed the user/fanrongl/add_nvfp4_mtp_tests branch from 0fc68ca to 6f5ff54 Compare June 17, 2025 12:05
@lfr-0531
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9203 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9203 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #6746 completed with status: 'FAILURE'

@lfr-0531 lfr-0531 force-pushed the user/fanrongl/add_nvfp4_mtp_tests branch from 6f5ff54 to d0fabb9 Compare June 18, 2025 01:42
@lfr-0531
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9272 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9272 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #6801 completed with status: 'FAILURE'

@lfr-0531 lfr-0531 force-pushed the user/fanrongl/add_nvfp4_mtp_tests branch from d0fabb9 to 0eb6847 Compare June 18, 2025 07:23
@lfr-0531
Copy link
Collaborator Author

/bot run --disable-fail-fast

1 similar comment
@lfr-0531
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9332 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9333 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9332 [ run ] completed with state ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9333 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #6850 completed with status: 'FAILURE'

lfr-0531 added 3 commits June 18, 2025 06:37
@lfr-0531
add nvfp4 mtp ds-lite tests.
e707d03 
Signed-off-by: Fanrong Li <[email protected]>
@lfr-0531
update tests.
7b14b3e 
Signed-off-by: Fanrong Li <[email protected]>
@lfr-0531
waive tests with moe_backend=TRTLLM
212216c 
Signed-off-by: Fanrong Li <[email protected]>
@lfr-0531 lfr-0531 force-pushed the user/fanrongl/add_nvfp4_mtp_tests branch from 0eb6847 to 212216c Compare June 18, 2025 13:42
@lfr-0531
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9402 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #9402 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #6898 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

@lfr-0531 lfr-0531 merged commit 6c3210a into NVIDIA:main Jun 19, 2025
3 checks passed
@lfr-0531 lfr-0531 deleted the user/fanrongl/add_nvfp4_mtp_tests branch June 27, 2025 12:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@hlu1 hlu1 hlu1 approved these changes

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
@lfr-0531 @tensorrt-cicd @hlu1