Skip to content

[https://nvbugs/6114139][test] Unwaive test_workers_kv_cache_events#15979

Merged
eopXD merged 1 commit into
NVIDIA:mainfrom
eopXD:unwaive-kv-cache-events-6114139
Jul 7, 2026
Merged

[https://nvbugs/6114139][test] Unwaive test_workers_kv_cache_events#15979
eopXD merged 1 commit into
NVIDIA:mainfrom
eopXD:unwaive-kv-cache-events-6114139

Conversation

@eopXD

@eopXD eopXD commented Jul 6, 2026

Copy link
Copy Markdown
Collaborator

Description

Re-enables disaggregated/test_workers.py::test_workers_kv_cache_events[TinyLlama-1.1B-Chat-v1.0], previously waived under NVBug 6114139.

The test was reproduced on a healthy GB300 (aarch64, sm_103, IMEX active) using a 1.3.0rc20 release container, and it passes with fabric memory active (mUseFabricMemory:1) and the NIXL/UCX cache transceiver. The original failure — tcp_ep ... send() failed: Input/output errorAgentConnection::send failedkNETWORK_ERROR — was an environment-specific UCX TCP KV-cache transfer failure (consistent with strict rp_filter on the failing node), not a code defect. Re-enabling so CI can validate.

Test Coverage

  • disaggregated/test_workers.py::test_workers_kv_cache_events[TinyLlama-1.1B-Chat-v1.0]

Summary by CodeRabbit

  • Tests
    • Removed an outdated test waiver from the integration test list.

Re-enable disaggregated/test_workers.py::test_workers_kv_cache_events[TinyLlama-1.1B-Chat-v1.0].

The test was reproduced on a healthy GB300 (aarch64, sm_103, IMEX active) using a
1.3.0rc20 release container and passes with fabric memory active. The original
failure was an environment-specific UCX TCP KV-cache transfer error, not a code
defect. Re-enabling so CI can validate.

Signed-off-by: Yueh-Ting Chen <yuehtingc@nvidia.com>
@eopXD

eopXD commented Jul 6, 2026

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@coderabbitai

coderabbitai Bot commented Jul 6, 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: d44c8d82-77c6-4504-a9a2-4e20bc35592e

📥 Commits

Reviewing files that changed from the base of the PR and between ef6ebc2 and 5f27a17.

📒 Files selected for processing (1)
  • tests/integration/test_lists/waives.txt
💤 Files with no reviewable changes (1)
  • tests/integration/test_lists/waives.txt

📝 Walkthrough

Walkthrough

A single waiver entry for the test disaggregated/test_workers.py::test_workers_kv_cache_events[TinyLlama-1.1B-Chat-v1.0] was removed from the test waiver list file.

Changes

Waiver list update

Layer / File(s) Summary
Remove unwaiver entry
tests/integration/test_lists/waives.txt
Removed the SKIP waiver entry for test_workers_kv_cache_events[TinyLlama-1.1B-Chat-v1.0], re-enabling the test.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Possibly related PRs

Suggested reviewers: yiqingy0, Superjomn

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title is concise and accurately describes re-enabling the waived test.
Description check ✅ Passed The description covers the change and test coverage, but the PR checklist section is not completed.
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.

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #57759 [ run ] triggered by Bot. Commit: 5f27a17 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #57759 [ run ] completed with state SUCCESS. Commit: 5f27a17
/LLM/main/L0_MergeRequest_PR pipeline #46463 completed with status: 'SUCCESS'

CI Report

Link to invocation

@eopXD eopXD merged commit 2817234 into NVIDIA:main Jul 7, 2026
11 checks passed
BrianLi23 pushed a commit to BrianLi23/TensorRT-LLM that referenced this pull request Jul 9, 2026
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