Skip to content

Conversation

moraxu
Copy link
Collaborator

@moraxu moraxu commented May 15, 2025

Description

Add CLI accuracy tests for Llama-3_3-Nemotron-Super-49B-v1 and LLM API FP8 variant.
CLI accuracy tests are still needed because NIMs use TRT-LLM's TRT backend for now.

Test Coverage

GitHub Bot Help

/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...

Provide a user friendly way for developers to interact with a Jenkins server.

Run /bot [-h|--help] to print this help message.

See details below for each supported subcommand.

run [--disable-fail-fast --skip-test --stage-list "A10-1, xxx" --gpu-type "A30, H100_PCIe" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-[Post-Merge]-1, xxx"]

Launch build/test pipelines. All previously running jobs will be killed.

--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.

--stage-list "A10-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-1, xxx". Note: Does NOT update GitHub check status.

--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.

--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.

--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests. Will also run L0 pre-merge pipeline.

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-[Post-Merge]-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-[Post-Merge]-1, xxx".

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

@moraxu moraxu requested review from Tracin and tijyojwad May 16, 2025 00:33
@moraxu moraxu force-pushed the add-cli-acc-tests-Llama-nemotron-Super-v1 branch from 6f77374 to 99bacee Compare May 17, 2025 04:16
@moraxu moraxu marked this pull request as ready for review May 17, 2025 04:17
@moraxu
Copy link
Collaborator Author

moraxu commented May 17, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5558 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5558 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #4055 completed with status: 'ABORTED'

@moraxu
Copy link
Collaborator Author

moraxu commented May 17, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5563 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5563 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #4060 completed with status: 'FAILURE'

@moraxu moraxu force-pushed the add-cli-acc-tests-Llama-nemotron-Super-v1 branch from 99bacee to d0fd9f7 Compare May 18, 2025 03:52
@moraxu
Copy link
Collaborator Author

moraxu commented May 18, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5587 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5587 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #4075 completed with status: 'FAILURE'

@moraxu moraxu force-pushed the add-cli-acc-tests-Llama-nemotron-Super-v1 branch from d0fd9f7 to c1f407a Compare May 18, 2025 20:13
@moraxu
Copy link
Collaborator Author

moraxu commented May 18, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5626 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5626 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #4110 completed with status: 'FAILURE'

@moraxu moraxu force-pushed the add-cli-acc-tests-Llama-nemotron-Super-v1 branch from c1f407a to d8e7799 Compare May 19, 2025 16:04
@moraxu
Copy link
Collaborator Author

moraxu commented May 19, 2025

/bot run

@moraxu moraxu requested review from syuoni and chang-l May 19, 2025 16:07
@tensorrt-cicd
Copy link
Collaborator

PR_Github #5749 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5749 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #4204 completed with status: 'FAILURE'

@moraxu
Copy link
Collaborator Author

moraxu commented May 19, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5779 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #5779 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #4231 completed with status: 'SUCCESS'

@moraxu moraxu requested a review from syuoni May 21, 2025 03:42
@moraxu moraxu changed the base branch from main to release/0.20 May 23, 2025 00:40
@moraxu moraxu requested a review from a team as a code owner May 23, 2025 00:40
@moraxu moraxu force-pushed the add-cli-acc-tests-Llama-nemotron-Super-v1 branch from 17a69a7 to 6f39ca9 Compare May 23, 2025 00:43
@moraxu
Copy link
Collaborator Author

moraxu commented May 23, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #6191 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #6191 [ run ] completed with state SUCCESS
/LLM/release-0.20/L0_MergeRequest_PR pipeline #48 completed with status: 'FAILURE'

@moraxu
Copy link
Collaborator Author

moraxu commented May 23, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #6322 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #6322 [ run ] completed with state SUCCESS
/LLM/release-0.20/L0_MergeRequest_PR pipeline #60 completed with status: 'SUCCESS'

@schetlur-nv schetlur-nv merged commit d2e6af2 into NVIDIA:release/0.20 May 23, 2025
3 checks passed
amirkl94 pushed a commit to amirkl94/TensorRT-LLM that referenced this pull request May 28, 2025
…-v1 and LLM API FP8 variant (NVIDIA#4375)

* Add CLI TestNemotronSuper acc tests

Signed-off-by: moraxu <[email protected]>

* Update mmlu.yaml

Signed-off-by: moraxu <[email protected]>

* Update yaml files

Signed-off-by: moraxu <[email protected]>

* Skip FP8 test in CLI

Signed-off-by: moraxu <[email protected]>

* Address reviews

Signed-off-by: moraxu <[email protected]>

* Address review comments

Signed-off-by: moraxu <[email protected]>

---------

Signed-off-by: moraxu <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants