[https://nvbugs/6266302][test] Unwaive test_disaggregated_llama_context_capacity by Tabrizian · Pull Request #15800 · NVIDIA/TensorRT-LLM

Tabrizian · 2026-06-30T20:57:58Z

Description

Unwaives the post-merge disaggregated test that was previously skipped under https://nvbugs/6266302:

disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_llama_context_capacity[False-False-DeepSeek-V3-Lite-fp8/fp8]

The underlying issue is not reproducible.

Test Coverage

disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_llama_context_capacity[False-False-DeepSeek-V3-Lite-fp8/fp8]

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.

Summary by CodeRabbit

Chores
- Removed one obsolete test waiver from the integration test list.
- No user-facing behavior changes were included.

Tabrizian · 2026-06-30T20:58:06Z

/bot run --disable-fail-fast

coderabbitai · 2026-06-30T20:59:02Z

📝 Walkthrough

Walkthrough

This change removes a single waiver entry from the test waivers list file, specifically the SKIP entry for test_disaggregated_llama_context_capacity with the [False-False-DeepSeek-V3-Lite-fp8/fp8] parameterization, re-enabling that test case in the disaggregated test suite.

Changes

Test waiver list update

Layer / File(s)	Summary
Remove waiver entry `tests/integration/test_lists/waives.txt`	Removes the SKIP waiver line for `test_disaggregated_llama_context_capacity` with `[False-False-DeepSeek-V3-Lite-fp8/fp8]` parameterization.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

NVIDIA/TensorRT-LLM#14450: Both PRs modify the same tests/integration/test_lists/waives.txt by adding/removing SKIP waiver entries.
NVIDIA/TensorRT-LLM#15561: Both PRs remove a SKIP waiver entry from the same waives.txt file.
NVIDIA/TensorRT-LLM#15779: Both PRs modify waives.txt with SKIP entries related to disaggregated tests.

Suggested reviewers

chzblych
niukuo
EmmaQiaoCh
yiqingy0
mzweilz

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title is specific and matches the main change: unwaiving the disaggregated test.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Description check	✅ Passed	The PR description follows the template, explains the change and rationale, and includes test coverage plus a completed checklist.

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests

_{Comment @coderabbitai help to get the list of available commands.}

Tabrizian · 2026-06-30T21:05:23Z

/bot run --stage-list "DGX_H100-PyTorch-4"

tensorrt-cicd · 2026-06-30T21:06:06Z

PR_Github #56725 [ run ] triggered by Bot. Commit: ba2e8e1 Link to invocation

…xt_capacity Unwaive disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_llama_context_capacity[False-False-DeepSeek-V3-Lite-fp8/fp8] which was skipped under https://nvbugs/6266302. Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

Tabrizian · 2026-06-30T21:10:03Z

/bot run --stage-list "DGX_H100-PyTorch-4"

tensorrt-cicd · 2026-06-30T21:12:03Z

PR_Github #56726 [ run ] triggered by Bot. Commit: 7e76e0f Link to invocation

tensorrt-cicd · 2026-06-30T21:15:47Z

PR_Github #56728 [ run ] triggered by Bot. Commit: 7e76e0f Link to invocation

tensorrt-cicd · 2026-06-30T21:16:24Z

PR_Github #56725 [ run ] completed with state ABORTED. Commit: ba2e8e1

Link to invocation

tensorrt-cicd · 2026-06-30T21:20:22Z

PR_Github #56726 [ run ] completed with state ABORTED. Commit: 7e76e0f

Link to invocation

tensorrt-cicd · 2026-07-01T00:03:07Z

PR_Github #56728 [ run ] completed with state SUCCESS. Commit: 7e76e0f
/LLM/main/L0_MergeRequest_PR pipeline #45547 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

Tabrizian · 2026-07-01T01:14:47Z

/bot run --stage-list "DGX_H100-PyTorch-1, DGX_H100-PyTorch-2, DGX_H100-PyTorch-3, DGX_H100-PyTorch-4, DGX_H100-PyTorch-5, DGX_H100-PyTorch-6"

tensorrt-cicd · 2026-07-01T01:20:23Z

PR_Github #56774 [ run ] triggered by Bot. Commit: 7e76e0f Link to invocation

tensorrt-cicd · 2026-07-01T02:23:16Z

PR_Github #56774 [ run ] completed with state FAILURE. Commit: 7e76e0f
/LLM/main/L0_MergeRequest_PR pipeline #45591 (Partly Tested) 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

Tabrizian · 2026-07-01T03:50:58Z

/bot run --disable-fail-fast --stage-list "DGX_H100-PyTorch-1, DGX_H100-PyTorch-2, DGX_H100-PyTorch-3, DGX_H100-PyTorch-4, DGX_H100-PyTorch-5, DGX_H100-PyTorch-6"

tensorrt-cicd · 2026-07-01T03:57:01Z

PR_Github #56822 [ run ] triggered by Bot. Commit: 7e76e0f Link to invocation

tensorrt-cicd · 2026-07-01T07:30:31Z

PR_Github #56822 [ run ] completed with state SUCCESS. Commit: 7e76e0f
/LLM/main/L0_MergeRequest_PR pipeline #45638 (Partly Tested) 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

Tabrizian · 2026-07-01T16:10:00Z

/bot run --disable-fail-fast --stage-list "DGX_H100-PyTorch-1, DGX_H100-PyTorch-2, DGX_H100-PyTorch-3, DGX_H100-PyTorch-4, DGX_H100-PyTorch-5, DGX_H100-PyTorch-6"

tensorrt-cicd · 2026-07-01T16:16:45Z

PR_Github #56968 [ run ] triggered by Bot. Commit: 7e76e0f Link to invocation

tensorrt-cicd · 2026-07-01T18:40:00Z

PR_Github #56968 [ run ] completed with state SUCCESS. Commit: 7e76e0f
/LLM/main/L0_MergeRequest_PR pipeline #45770 (Partly Tested) 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

Tabrizian · 2026-07-01T18:46:59Z

/bot run --disable-fail-fast --stage-list "DGX_H100-PyTorch-1, DGX_H100-PyTorch-2, DGX_H100-PyTorch-3, DGX_H100-PyTorch-4, DGX_H100-PyTorch-5, DGX_H100-PyTorch-6"

tensorrt-cicd · 2026-07-01T18:53:01Z

PR_Github #57005 [ run ] triggered by Bot. Commit: 7e76e0f Link to invocation

tensorrt-cicd · 2026-07-01T19:34:48Z

PR_Github #57005 [ run ] completed with state SUCCESS. Commit: 7e76e0f
/LLM/main/L0_MergeRequest_PR pipeline #45804 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

Tabrizian · 2026-07-01T19:39:03Z

/bot skip --comment "test stage has passed"

brb-nv

LGTM.

tensorrt-cicd · 2026-07-01T19:46:19Z

PR_Github #57014 [ skip ] triggered by Bot. Commit: 7e76e0f Link to invocation

tensorrt-cicd · 2026-07-01T19:53:23Z

PR_Github #57014 [ skip ] completed with state SUCCESS. Commit: 7e76e0f
Skipping testing for commit 7e76e0f

Link to invocation

…xt_capacity (NVIDIA#15800) Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

github-actions Bot assigned Tabrizian Jun 30, 2026

Tabrizian force-pushed the unwaive-disagg-context-capacity-6266302 branch from ba2e8e1 to 7e76e0f Compare June 30, 2026 21:09

Tabrizian enabled auto-merge (squash) July 1, 2026 19:39

Tabrizian requested a review from brb-nv July 1, 2026 19:40

brb-nv approved these changes Jul 1, 2026

View reviewed changes

Tabrizian merged commit 50ea42a into NVIDIA:main Jul 1, 2026
8 checks passed

This was referenced Jul 2, 2026

[https://nvbugs/6321874][test] Unwaive test_autotuner_distributed_str… #15864

Closed

[https://nvbugs/6384622][fix] increase free_mem_frac for failed perf test #15879

Merged

evezhier pushed a commit to evezhier/TensorRT-LLM that referenced this pull request Jul 2, 2026

[https://nvbugs/6266302][test] Unwaive test_disaggregated_llama_conte…

f45ad8b

…xt_capacity (NVIDIA#15800) Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

BrianLi23 pushed a commit to BrianLi23/TensorRT-LLM that referenced this pull request Jul 9, 2026

[https://nvbugs/6266302][test] Unwaive test_disaggregated_llama_conte…

2a65114

…xt_capacity (NVIDIA#15800) Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

Uh oh!

Conversation

Tabrizian commented Jun 30, 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

Summary by CodeRabbit

Uh oh!

Tabrizian commented Jun 30, 2026

Uh oh!

coderabbitai Bot commented Jun 30, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Suggested reviewers

Uh oh!

Tabrizian commented Jun 30, 2026

Uh oh!

tensorrt-cicd commented Jun 30, 2026

Uh oh!

Tabrizian commented Jun 30, 2026

Uh oh!

tensorrt-cicd commented Jun 30, 2026

Uh oh!

tensorrt-cicd commented Jun 30, 2026

Uh oh!

tensorrt-cicd commented Jun 30, 2026

Uh oh!

tensorrt-cicd commented Jun 30, 2026

Uh oh!

tensorrt-cicd commented Jul 1, 2026

Uh oh!

Tabrizian commented Jul 1, 2026

Uh oh!

tensorrt-cicd commented Jul 1, 2026

Uh oh!

tensorrt-cicd commented Jul 1, 2026

Uh oh!

Tabrizian commented Jul 1, 2026

Uh oh!

tensorrt-cicd commented Jul 1, 2026

Uh oh!

tensorrt-cicd commented Jul 1, 2026

Uh oh!

Tabrizian commented Jul 1, 2026

Uh oh!

tensorrt-cicd commented Jul 1, 2026

Uh oh!

tensorrt-cicd commented Jul 1, 2026

Uh oh!

Tabrizian commented Jul 1, 2026

Uh oh!

tensorrt-cicd commented Jul 1, 2026

Uh oh!

tensorrt-cicd commented Jul 1, 2026

Uh oh!

Tabrizian commented Jul 1, 2026

Uh oh!

brb-nv left a comment

Choose a reason for hiding this comment

Uh oh!

tensorrt-cicd commented Jul 1, 2026

Uh oh!

tensorrt-cicd commented Jul 1, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Tabrizian commented Jun 30, 2026 •

edited

Loading

coderabbitai Bot commented Jun 30, 2026 •

edited

Loading