[None][infra] Waive 1 failed cases for main in post-merge - #12390
[None][infra] Waive 1 failed cases for main in post-merge#12390xinhe-nv wants to merge 1 commit into
Conversation
Bug(s): 5756008 Requested by: qa@nvidia.com Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
📝 WalkthroughWalkthroughAdded a single waiver entry to the test skip list for Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
📝 Coding Plan
Comment |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@tests/integration/test_lists/waives.txt`:
- Line 375: The waiver entry at line containing
"TestLlama3_1_8BInstruct::test_guided_decoding_4gpus[llguidance]" is missing the
required file path prefix; update that waiver string to include the full path
prefix "accuracy/test_llm_api.py::" so it matches the other entry for the same
test class (e.g., change
"TestLlama3_1_8BInstruct::test_guided_decoding_4gpus[llguidance]" to
"accuracy/test_llm_api.py::TestLlama3_1_8BInstruct::test_guided_decoding_4gpus[llguidance]")
to ensure the test framework recognizes the waiver.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: e2f46dda-a078-44f3-a62f-af1760c63756
📒 Files selected for processing (1)
tests/integration/test_lists/waives.txt
| perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-r1-fp4_1k1k_con2048_ctx2_dep4_gen1_dep16_eplb0_mtp3_ccb-UCX] SKIP (https://nvbugs/5996645) | ||
| perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb200_deepseek-r1-fp4_1k1k_con2048_ctx2_dep4_gen1_dep16_eplb288_mtp3_ccb-UCX] SKIP (https://nvbugs/5997090) | ||
| perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_v32_fp4_blackwell-v32_fp4_tep8_mtp3_8k1k] SKIP (https://nvbugs/5997092) | ||
| TestLlama3_1_8BInstruct::test_guided_decoding_4gpus[llguidance] SKIP (https://nvbugs/5756008) |
There was a problem hiding this comment.
Missing file path prefix in waiver entry.
The new waiver entry is missing the file path prefix accuracy/test_llm_api.py:: that appears in the similar entry at line 121 for the same test class. All other entries in this file include their full path (e.g., examples/, accuracy/, perf/, etc.).
Compare:
- Line 121:
accuracy/test_llm_api.py::TestLlama3_1_8BInstruct::test_guided_decoding_4gpus[xgrammar] - Line 375:
TestLlama3_1_8BInstruct::test_guided_decoding_4gpus[llguidance](missing path)
Without the correct path prefix, the waiver may not be recognized by the test framework.
🔧 Proposed fix
-TestLlama3_1_8BInstruct::test_guided_decoding_4gpus[llguidance] SKIP (https://nvbugs/5756008)
+accuracy/test_llm_api.py::TestLlama3_1_8BInstruct::test_guided_decoding_4gpus[llguidance] SKIP (https://nvbugs/5756008)📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| TestLlama3_1_8BInstruct::test_guided_decoding_4gpus[llguidance] SKIP (https://nvbugs/5756008) | |
| accuracy/test_llm_api.py::TestLlama3_1_8BInstruct::test_guided_decoding_4gpus[llguidance] SKIP (https://nvbugs/5756008) |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@tests/integration/test_lists/waives.txt` at line 375, The waiver entry at
line containing
"TestLlama3_1_8BInstruct::test_guided_decoding_4gpus[llguidance]" is missing the
required file path prefix; update that waiver string to include the full path
prefix "accuracy/test_llm_api.py::" so it matches the other entry for the same
test class (e.g., change
"TestLlama3_1_8BInstruct::test_guided_decoding_4gpus[llguidance]" to
"accuracy/test_llm_api.py::TestLlama3_1_8BInstruct::test_guided_decoding_4gpus[llguidance]")
to ensure the test framework recognizes the waiver.
Auto-generated Waive PR
Created by: TensorRT LLM CI Report (requested by qa@nvidia.com)
Target branch:
mainBug(s): 5756008
Waive entries added
This PR was auto-generated by TensorRT LLM CI Report. Please review the waive entries before merging.
Summary by CodeRabbit
Note: This release contains no end-user visible changes. The update is limited to internal test infrastructure.