TensorRT-LLM icon indicating copy to clipboard operation
TensorRT-LLM copied to clipboard

fix/ replace sanity test for nemotron h with a correctness test

Open omera-nv opened this issue 8 months ago • 9 comments

[TRTLLM-5085][fix] Nemotron H correctness test

Description

Nemotron H was lacking a correctness test due to a missing public reference. This PR replaces the basic sanity test with a proper correctness test against known good outputs from mcore.

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.

omera-nv avatar May 08 '25 07:05 omera-nv

/bot run

omera-nv avatar May 08 '25 07:05 omera-nv

PR_Github #4514 [ run ] triggered by Bot

tensorrt-cicd avatar May 08 '25 07:05 tensorrt-cicd

PR_Github #4514 [ run ] completed with state SUCCESS /LLM/main/L0_MergeRequest_PR pipeline #3246 completed with status: 'FAILURE'

tensorrt-cicd avatar May 08 '25 10:05 tensorrt-cicd

/bot run

omera-nv avatar May 08 '25 11:05 omera-nv

PR_Github #4546 [ run ] triggered by Bot

tensorrt-cicd avatar May 08 '25 11:05 tensorrt-cicd

PR_Github #4546 [ run ] completed with state SUCCESS /LLM/main/L0_MergeRequest_PR pipeline #3268 completed with status: 'FAILURE'

tensorrt-cicd avatar May 08 '25 13:05 tensorrt-cicd

/bot run

omera-nv avatar May 12 '25 08:05 omera-nv

PR_Github #4862 [ run ] triggered by Bot

tensorrt-cicd avatar May 12 '25 08:05 tensorrt-cicd

PR_Github #4862 [ run ] completed with state SUCCESS /LLM/main/L0_MergeRequest_PR pipeline #3520 completed with status: 'SUCCESS'

tensorrt-cicd avatar May 12 '25 14:05 tensorrt-cicd

/bot run

tomeras91 avatar May 18 '25 13:05 tomeras91

PR_Github #5616 [ run ] triggered by Bot

tensorrt-cicd avatar May 18 '25 13:05 tensorrt-cicd

PR_Github #5616 [ run ] completed with state SUCCESS /LLM/main/L0_MergeRequest_PR pipeline #4101 completed with status: 'FAILURE'

tensorrt-cicd avatar May 18 '25 16:05 tensorrt-cicd

/bot run

tomeras91 avatar May 18 '25 16:05 tomeras91

PR_Github #5623 [ run ] triggered by Bot

tensorrt-cicd avatar May 18 '25 16:05 tensorrt-cicd

PR_Github #5623 [ run ] completed with state FAILURE /LLM/main/L0_MergeRequest_PR pipeline #4107 completed with status: 'FAILURE'

tensorrt-cicd avatar May 18 '25 18:05 tensorrt-cicd

/bot run

tomeras91 avatar May 18 '25 20:05 tomeras91

PR_Github #5628 [ run ] triggered by Bot

tensorrt-cicd avatar May 18 '25 20:05 tensorrt-cicd

PR_Github #5628 [ run ] completed with state SUCCESS /LLM/main/L0_MergeRequest_PR pipeline #4112 completed with status: 'SUCCESS'

tensorrt-cicd avatar May 18 '25 22:05 tensorrt-cicd

/bot run

tomeras91 avatar May 19 '25 11:05 tomeras91

/bot run

netanel-haber avatar May 19 '25 12:05 netanel-haber

Replaced by PR #4444

tomeras91 avatar May 19 '25 15:05 tomeras91