Skip to content

[None][infra] Waive 4 failed cases for main in post-merge 2827 - #16169

Merged
mzweilz merged 1 commit into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260709-034526
Jul 9, 2026
Merged

[None][infra] Waive 4 failed cases for main in post-merge 2827#16169
mzweilz merged 1 commit into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260709-034526

Conversation

@trtllm-agent

@trtllm-agent trtllm-agent commented Jul 9, 2026

Copy link
Copy Markdown
Collaborator

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by @mzweilz)
Target branch: main
Bug(s): 6432818, 6432826, 6432831, 6432832, 6432948

Waive entries added

disaggregated/test_disaggregated.py::test_disaggregated_mixed_stress_test[req60-conc64-qwen3_32b_fp8_mixed_stress] SKIP (https://nvbugs/6432832)
full:DGX_B300/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[ep4-mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False] SKIP (https://nvbugs/6432831)
perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp8_blackwell-r1_fp8_tp8_mtp3_8k1k] SKIP (https://nvbugs/6432948)
unittest/llmapi/test_llm_multi_gpu_pytorch.py::test_llm_get_stats_pp2[False-False-True] SKIP (https://nvbugs/6432826)

Already waived (skipped)

  • accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales_4gpus[pp4-mtp_nextn=0-fp8kv=True-attention_dp=False-cuda_graph=True-overlap_scheduler=True-torch_compile=True-sampler_async_worker=False]

This PR was auto-generated by TensorRT LLM CI Report. Please review the waive entries before merging.

Summary by CodeRabbit

  • Bug Fixes
    • Updated the test waiver list to skip four additional test cases with known issues, helping keep automated runs stable and reduce noise from expected failures.

Bug(s): 6432818, 6432826, 6432831, 6432832, 6432948
Requested by: @mzweilz

Signed-off-by: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com>
@coderabbitai

coderabbitai Bot commented Jul 9, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 9cc2b1d3-cf79-46a3-8c5a-96be8dff5447

📥 Commits

Reviewing files that changed from the base of the PR and between 60583d2 and 3e01901.

📒 Files selected for processing (1)
  • tests/integration/test_lists/waives.txt

📝 Walkthrough

Walkthrough

Four new SKIP waiver entries were added to tests/integration/test_lists/waives.txt, referencing nvbugs 6432832, 6432831, 6432948, and 6432826, covering a disaggregated stress test, a DeepSeekV3Lite accuracy test, a perf sanity e2e test, and a multi-GPU llmapi stats test.

Changes

Test waiver additions

Layer / File(s) Summary
Add new SKIP waiver entries
tests/integration/test_lists/waives.txt
Four SKIP lines added waiving test_disaggregated_mixed_stress_test, TestDeepSeekV3Lite::test_bfloat16_4gpus, perf/test_perf_sanity.py::test_e2e, and test_llm_get_stats_pp2 for specific parameter configurations, each tied to a distinct nvbugs reference.

Estimated code review effort: 1 (Trivial) | ~3 minutes

Possibly related PRs

  • NVIDIA/TensorRT-LLM#16109: Both PRs add SKIP waivers for the same set of test types (disaggregated, DeepSeekV3Lite bfloat16_4gpus, perf_sanity e2e, and llmapi multi-GPU stats) in waives.txt.
  • NVIDIA/TensorRT-LLM#16127: Both PRs add waivers for the test_llm_get_stats_pp* multi-GPU llmapi test in waives.txt.
  • NVIDIA/TensorRT-LLM#15825: Both PRs add overlapping SKIP entries for TestDeepSeekV3Lite::test_bfloat16_4gpus and perf/test_perf_sanity.py::test_e2e in waives.txt.

Suggested reviewers: mzweilz, yuxianq, dongxuy04

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title matches the PR's main change and follows the required [None][infra] summary pattern.
Description check ✅ Passed The description states the waivers added, linked bugs, and existing skip, covering the PR's intent sufficiently.
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.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

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

@mzweilz

mzweilz commented Jul 9, 2026

Copy link
Copy Markdown
Collaborator

/bot skip --comment "waive only"

@mzweilz
mzweilz enabled auto-merge (squash) July 9, 2026 05:08
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #58375 [ skip ] triggered by Bot. Commit: 3e01901 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #58375 [ skip ] completed with state SUCCESS. Commit: 3e01901
Skipping testing for commit 3e01901

Link to invocation

@mzweilz
mzweilz merged commit 50f0bf4 into NVIDIA:main Jul 9, 2026
12 checks passed
mingyangHao added a commit to mingyangHao/TensorRT-LLM that referenced this pull request Jul 9, 2026
Remove the PP sampler waivers introduced by NVIDIA#16103, NVIDIA#16105, NVIDIA#16127, and NVIDIA#16146. Also remove overlapping PP and gpu2 waivers from NVIDIA#16109, plus the PP2 waiver added by NVIDIA#16169, so the restored pre-NVIDIA#15920 sampler path is exercised in CI.

Signed-off-by: Mingyang Hao <200044211+mingyangHao@users.noreply.github.com>
mingyangHao added a commit to mingyangHao/TensorRT-LLM that referenced this pull request Jul 9, 2026
Remove the PP sampler waivers introduced by NVIDIA#16103, NVIDIA#16105, NVIDIA#16127, and NVIDIA#16146. Also remove overlapping PP and gpu2 waivers from NVIDIA#16109, plus the PP2 waiver added by NVIDIA#16169, so the restored pre-NVIDIA#15920 sampler path is exercised in CI.

Signed-off-by: Mingyang Hao <200044211+mingyangHao@users.noreply.github.com>
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.

3 participants