[None][test] Add DeepSeek V4 Pro disagg tests by lfr-0531 · Pull Request #14236 · NVIDIA/TensorRT-LLM

lfr-0531 · 2026-05-18T03:28:59Z

Add DeepSeek V4 Pro disaggregated serving test configs for TEP8 and DEP16 gen-only coverage, plus a DEP16 e2e configuration for GB200-scale validation.

@coderabbitai summary

Description

Test Coverage

PR Checklist

Please review the following before submitting your PR:

PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

lfr-0531 · 2026-05-18T04:16:12Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-05-18T04:22:02Z

PR_Github #48830 [ run ] triggered by Bot. Commit: abe9c4a Link to invocation

tensorrt-cicd · 2026-05-18T07:01:52Z

PR_Github #48830 [ run ] completed with state SUCCESS. Commit: abe9c4a
/LLM/main/L0_MergeRequest_PR pipeline #38590 completed with status: 'SUCCESS'

CI Report

Link to invocation

lfr-0531 · 2026-05-18T09:08:32Z

/bot help

github-actions · 2026-05-18T09:08:42Z

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.

Details

run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental) --high-priority]

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

--reuse-test (optional)pipeline-id (OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.

--disable-reuse-test (OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.

--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-PyTorch-1, xxx" (OPTIONAL) : Only run the specified test stages. Supports wildcard * for pattern matching (e.g., "*PerfSanity*" matches all stages containing PerfSanity). Examples: "A10-PyTorch-1, xxx", "PerfSanity". 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.

--test-backend "pytorch, cpp" (OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline 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 in addition to running 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-TensorRT-Post-Merge-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Supports wildcard * for pattern matching. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx", --extra-stage "Post-Merge".

--detailed-log (OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.

--debug (OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in the stage-list parameter to access the appropriate container environment. Note: Does NOT update GitHub check status.

--high-priority (OPTIONAL) : Run the pipeline with high priority. This option is restricted to authorized users only and will route the job to a high-priority queue.

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.

lfr-0531 · 2026-05-18T09:09:05Z

/bot run --disable-fail-fast --post-merge

tensorrt-cicd · 2026-05-18T09:15:44Z

PR_Github #48884 [ run ] triggered by Bot. Commit: 72b6290 Link to invocation

tensorrt-cicd · 2026-05-18T14:21:48Z

PR_Github #48884 [ run ] completed with state SUCCESS. Commit: 72b6290
/LLM/main/L0_MergeRequest_PR pipeline #38634 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

lfr-0531 · 2026-05-18T15:59:33Z

/bot run --disable-fail-fast --post-merge

tensorrt-cicd · 2026-05-18T16:07:42Z

PR_Github #48934 [ run ] triggered by Bot. Commit: 18c7737 Link to invocation

tensorrt-cicd · 2026-05-18T17:44:09Z

PR_Github #48934 [ run ] completed with state SUCCESS. Commit: 18c7737
/LLM/main/L0_MergeRequest_PR pipeline #38681 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

lfr-0531 · 2026-05-19T01:29:23Z

/bot run --disable-fail-fast --post-merge

tensorrt-cicd · 2026-05-19T01:38:15Z

PR_Github #49028 [ run ] triggered by Bot. Commit: 18c7737 Link to invocation

lfr-0531 · 2026-05-19T10:27:52Z

/bot kill

tensorrt-cicd · 2026-05-19T10:33:56Z

PR_Github #49175 [ kill ] triggered by Bot. Commit: e61c2ac Link to invocation

tensorrt-cicd · 2026-05-19T10:38:09Z

PR_Github #49028 [ run ] completed with state ABORTED. Commit: 18c7737

Link to invocation

tensorrt-cicd · 2026-05-19T10:38:20Z

PR_Github #49175 [ kill ] completed with state SUCCESS. Commit: e61c2ac
Successfully killed previous jobs for commit e61c2ac

Link to invocation

lfr-0531 · 2026-05-19T10:44:21Z

/bot run --disable-fail-fast --post-merge

tensorrt-cicd · 2026-05-19T10:50:42Z

PR_Github #49178 [ run ] triggered by Bot. Commit: b2b7ffe Link to invocation

tensorrt-cicd · 2026-05-19T15:06:07Z

PR_Github #49178 [ run ] completed with state SUCCESS. Commit: b2b7ffe
/LLM/main/L0_MergeRequest_PR pipeline #38856 completed with status: 'SUCCESS'

CI Report

Link to invocation

tensorrt-cicd · 2026-05-21T13:53:55Z

PR_Github #49709 [ run ] triggered by Bot. Commit: 850c923 Link to invocation

tensorrt-cicd · 2026-05-21T13:55:52Z

PR_Github #49698 [ run ] completed with state ABORTED. Commit: cd80e14

Link to invocation

lfr-0531 · 2026-05-21T14:39:52Z

/bot run --disable-fail-fast --post-merge

tensorrt-cicd · 2026-05-21T14:46:13Z

PR_Github #49719 [ run ] triggered by Bot. Commit: 850c923 Link to invocation

tensorrt-cicd · 2026-05-21T14:48:09Z

PR_Github #49709 [ run ] completed with state ABORTED. Commit: 850c923

Link to invocation

tensorrt-cicd · 2026-05-21T19:25:02Z

PR_Github #49719 [ run ] completed with state SUCCESS. Commit: 850c923
/LLM/main/L0_MergeRequest_PR pipeline #39325 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

Shixiaowei02 · 2026-05-22T07:23:42Z

/bot run --disable-fail-fast --post-merge

tensorrt-cicd · 2026-05-22T07:30:07Z

PR_Github #49885 [ run ] triggered by Bot. Commit: 881b259 Link to invocation

tensorrt-cicd · 2026-05-22T12:28:49Z

PR_Github #49885 [ run ] completed with state SUCCESS. Commit: 881b259
/LLM/main/L0_MergeRequest_PR pipeline #39463 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

lfr-0531 · 2026-05-25T11:39:00Z

/bot run --disable-fail-fast --post-merge

tensorrt-cicd · 2026-05-25T11:45:22Z

PR_Github #50214 [ run ] triggered by Bot. Commit: 1f8ae89 Link to invocation

Add DeepSeek V4 Pro disaggregated serving test configs for TEP8 and DEP16 gen-only coverage, plus a DEP16 e2e configuration for GB200-scale validation. Signed-off-by: Fanrong Li <lfr-0531@users.noreply.github.com>

Add the DeepSeek V4 Pro disaggregated serving tests to the GB200 DS pre-merge test list with separate 8, 16, and 24 GPU resource blocks for their required parallelism. Signed-off-by: Fanrong Li <lfr-0531@users.noreply.github.com>

Signed-off-by: Fanrong Li <lfr-0531@users.noreply.github.com>

Signed-off-by: Xiaowei Shi <39303645+Shixiaowei02@users.noreply.github.com>

Signed-off-by: Fanrong Li <lfr-0531@users.noreply.github.com>

…orker Signed-off-by: Xiaowei Shi <39303645+Shixiaowei02@users.noreply.github.com>

Signed-off-by: Fanrong Li <lfr-0531@users.noreply.github.com>

…e via MPI Signed-off-by: Xiaowei Shi <39303645+Shixiaowei02@users.noreply.github.com>

Shixiaowei02 · 2026-05-25T15:02:32Z

/bot run --disable-fail-fast --post-merge

tensorrt-cicd · 2026-05-25T15:08:41Z

PR_Github #50224 [ run ] triggered by Bot. Commit: 6fb321c Link to invocation

tensorrt-cicd · 2026-05-25T15:09:12Z

PR_Github #50225 [ run ] triggered by Bot. Commit: 6fb321c Link to invocation

tensorrt-cicd · 2026-05-25T15:09:16Z

PR_Github #50224 [ run ] completed with state ABORTED. Commit: 6fb321c

Link to invocation

tensorrt-cicd · 2026-05-25T15:09:40Z

PR_Github #50214 [ run ] completed with state ABORTED. Commit: 1f8ae89

Link to invocation

github-actions Bot assigned lfr-0531 May 18, 2026

lfr-0531 marked this pull request as ready for review May 20, 2026 02:59

lfr-0531 requested review from a team as code owners May 20, 2026 02:59

lfr-0531 requested review from mlefeb01 and yuanjingx87 and removed request for a team May 20, 2026 02:59

lfr-0531 marked this pull request as draft May 20, 2026 03:25

Shixiaowei02 force-pushed the user/fanrongl/add-dsv4-pro-disagg-tests branch from 850c923 to 881b259 Compare May 22, 2026 07:23

lfr-0531 and others added 12 commits May 25, 2026 23:02

[None][test] Add DeepSeek V4 Pro disagg tests

a9b502c

Add DeepSeek V4 Pro disaggregated serving test configs for TEP8 and DEP16 gen-only coverage, plus a DEP16 e2e configuration for GB200-scale validation. Signed-off-by: Fanrong Li <lfr-0531@users.noreply.github.com>

[None][test] Add DeepSeek V4 Pro tests to GB200 list

c5cc7d9

Add the DeepSeek V4 Pro disaggregated serving tests to the GB200 DS pre-merge test list with separate 8, 16, and 24 GPU resource blocks for their required parallelism. Signed-off-by: Fanrong Li <lfr-0531@users.noreply.github.com>

[None][test] Add GB200 DS stages

e2ea9dd

Signed-off-by: Fanrong Li <lfr-0531@users.noreply.github.com>

[None][test] Move large GB200 DS tests to post merge

78b1352

Signed-off-by: Fanrong Li <lfr-0531@users.noreply.github.com>

[None][test] Use registered GB200 Slurm platform

9888a46

Signed-off-by: Fanrong Li <lfr-0531@users.noreply.github.com>

[None][test] Fix GB200 multinode Slurm args

8665cfa

Signed-off-by: Fanrong Li <lfr-0531@users.noreply.github.com>

[None][test] Use GB200 flex platform for multinode DS

5f90592

Signed-off-by: Fanrong Li <lfr-0531@users.noreply.github.com>

avoid test skipping

6208f06

Signed-off-by: Xiaowei Shi <39303645+Shixiaowei02@users.noreply.github.com>

[None][test] Move DSv4 Pro disagg tests to GB300

c791861

Signed-off-by: Fanrong Li <lfr-0531@users.noreply.github.com>

[None][test] Multi-instance multi-node disagg via disaggregated_mpi_w…

01f818d

…orker Signed-off-by: Xiaowei Shi <39303645+Shixiaowei02@users.noreply.github.com>

[None][test] Fix multinode DSv4 Pro disagg CI cleanup

519716d

Signed-off-by: Fanrong Li <lfr-0531@users.noreply.github.com>

Multinode disagg: gate DeepEPLowLatency NVSHMEM and ship config inlin…

6fb321c

…e via MPI Signed-off-by: Xiaowei Shi <39303645+Shixiaowei02@users.noreply.github.com>

Shixiaowei02 force-pushed the user/fanrongl/add-dsv4-pro-disagg-tests branch from d6e8253 to 6fb321c Compare May 25, 2026 15:02

Conversation

lfr-0531 commented May 18, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Test Coverage

PR Checklist

GitHub Bot Help

Uh oh!

lfr-0531 commented May 18, 2026

Uh oh!

tensorrt-cicd commented May 18, 2026

Uh oh!

tensorrt-cicd commented May 18, 2026

Uh oh!

lfr-0531 commented May 18, 2026

Uh oh!

github-actions Bot commented May 18, 2026

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

lfr-0531 commented May 18, 2026

Uh oh!

tensorrt-cicd commented May 18, 2026

Uh oh!

tensorrt-cicd commented May 18, 2026

Uh oh!

lfr-0531 commented May 18, 2026

Uh oh!

tensorrt-cicd commented May 18, 2026

Uh oh!

tensorrt-cicd commented May 18, 2026

Uh oh!

lfr-0531 commented May 19, 2026

Uh oh!

tensorrt-cicd commented May 19, 2026

Uh oh!

lfr-0531 commented May 19, 2026

Uh oh!

tensorrt-cicd commented May 19, 2026

Uh oh!

tensorrt-cicd commented May 19, 2026

Uh oh!

tensorrt-cicd commented May 19, 2026

Uh oh!

lfr-0531 commented May 19, 2026

Uh oh!

tensorrt-cicd commented May 19, 2026

Uh oh!

tensorrt-cicd commented May 19, 2026

Uh oh!

tensorrt-cicd commented May 21, 2026

Uh oh!

tensorrt-cicd commented May 21, 2026

Uh oh!

lfr-0531 commented May 21, 2026

Uh oh!

tensorrt-cicd commented May 21, 2026

Uh oh!

tensorrt-cicd commented May 21, 2026

Uh oh!

tensorrt-cicd commented May 21, 2026

Uh oh!

Shixiaowei02 commented May 22, 2026

Uh oh!

tensorrt-cicd commented May 22, 2026

Uh oh!

tensorrt-cicd commented May 22, 2026

Uh oh!

lfr-0531 commented May 25, 2026

Uh oh!

tensorrt-cicd commented May 25, 2026

Uh oh!

Shixiaowei02 commented May 25, 2026

Uh oh!

tensorrt-cicd commented May 25, 2026

Uh oh!

tensorrt-cicd commented May 25, 2026

Uh oh!

lfr-0531 commented May 18, 2026 •

edited

Loading