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

[https://nvbugs/5123103][fix] Fix torch compile for DeepSeekV3

Open liji-nv opened this issue 9 months ago • 89 comments

PR title

Please write the PR title by following template:

[JIRA ticket link/nvbug link/github issue link][fix/feat/doc/infra/...] <summary of this PR>

For example, assume I have a PR hope to support a new feature about cache manager of Jira TRTLLM-1000 ticket, it would be like

[TRTLLM-1000][feat] Support a new feature about cache manager

Description

Please explain the issue and the solution in short.

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.

liji-nv avatar Apr 29 '25 11:04 liji-nv

/bot run

liji-nv avatar Apr 30 '25 02:04 liji-nv

PR_Github #3789 [ run ] triggered by Bot

tensorrt-cicd avatar Apr 30 '25 02:04 tensorrt-cicd

PR_Github #3789 [ run ] completed with state SUCCESS /LLM/main/L0_MergeRequest_PR pipeline #2682 completed with status: 'FAILURE'

tensorrt-cicd avatar Apr 30 '25 03:04 tensorrt-cicd

/bot run

liji-nv avatar Apr 30 '25 03:04 liji-nv

/bot kill

liji-nv avatar Apr 30 '25 04:04 liji-nv

PR_Github #3796 [ run ] triggered by Bot

tensorrt-cicd avatar Apr 30 '25 04:04 tensorrt-cicd

PR_Github #3797 [ kill ] triggered by Bot

tensorrt-cicd avatar Apr 30 '25 04:04 tensorrt-cicd

PR_Github #3796 [ run ] completed with state ABORTED

tensorrt-cicd avatar Apr 30 '25 04:04 tensorrt-cicd

PR_Github #3797 [ kill ] completed with state SUCCESS Successfully killed previous jobs for commit d1bbc5c

tensorrt-cicd avatar Apr 30 '25 04:04 tensorrt-cicd

/bot run

liji-nv avatar Apr 30 '25 04:04 liji-nv

PR_Github #3798 [ run ] triggered by Bot

tensorrt-cicd avatar Apr 30 '25 04:04 tensorrt-cicd

PR_Github #3798 [ run ] completed with state SUCCESS /LLM/main/L0_MergeRequest_PR pipeline #2687 completed with status: 'FAILURE'

tensorrt-cicd avatar Apr 30 '25 06:04 tensorrt-cicd

/bot run

liji-nv avatar Apr 30 '25 08:04 liji-nv

PR_Github #3826 [ run ] triggered by Bot

tensorrt-cicd avatar Apr 30 '25 08:04 tensorrt-cicd

/bot kill

liji-nv avatar Apr 30 '25 08:04 liji-nv

PR_Github #3828 [ kill ] triggered by Bot

tensorrt-cicd avatar Apr 30 '25 08:04 tensorrt-cicd

PR_Github #3826 [ run ] completed with state ABORTED

tensorrt-cicd avatar Apr 30 '25 08:04 tensorrt-cicd

PR_Github #3828 [ kill ] completed with state SUCCESS Successfully killed previous jobs for commit 98043dc

tensorrt-cicd avatar Apr 30 '25 08:04 tensorrt-cicd

/bot run

liji-nv avatar Apr 30 '25 08:04 liji-nv

PR_Github #3829 [ run ] triggered by Bot

tensorrt-cicd avatar Apr 30 '25 08:04 tensorrt-cicd

/bot run --disable-fail-fast

liji-nv avatar Apr 30 '25 10:04 liji-nv

PR_Github #3843 [ run ] triggered by Bot

tensorrt-cicd avatar Apr 30 '25 10:04 tensorrt-cicd

PR_Github #3829 [ run ] completed with state ABORTED /LLM/main/L0_MergeRequest_PR pipeline #2711 completed with status: 'FAILURE'

tensorrt-cicd avatar Apr 30 '25 10:04 tensorrt-cicd

PR_Github #3843 [ run ] completed with state SUCCESS /LLM/main/L0_MergeRequest_PR pipeline #2723 completed with status: 'FAILURE'

tensorrt-cicd avatar Apr 30 '25 13:04 tensorrt-cicd

/bot run

liji-nv avatar May 06 '25 12:05 liji-nv

PR_Github #4207 [ run ] triggered by Bot

tensorrt-cicd avatar May 06 '25 12:05 tensorrt-cicd

PR_Github #4207 [ run ] completed with state FAILURE /LLM/main/L0_MergeRequest_PR pipeline #3007 completed with status: 'FAILURE'

tensorrt-cicd avatar May 06 '25 13:05 tensorrt-cicd

/bot run

liji-nv avatar May 07 '25 02:05 liji-nv

PR_Github #4296 [ run ] triggered by Bot

tensorrt-cicd avatar May 07 '25 02:05 tensorrt-cicd

PR_Github #4296 [ run ] completed with state SUCCESS /LLM/main/L0_MergeRequest_PR pipeline #3077 completed with status: 'FAILURE'

tensorrt-cicd avatar May 07 '25 04:05 tensorrt-cicd