Skip to content

[TRTLLM-15177][test] Wire remaining Kimi K3 MoE unit tests into L0 (Hopper) - #17711

Merged
brnguyen2 merged 1 commit into
NVIDIA:mainfrom
brnguyen2:k3/15177-wire-moe-unit-tests
Aug 16, 2026
Merged

[TRTLLM-15177][test] Wire remaining Kimi K3 MoE unit tests into L0 (Hopper)#17711
brnguyen2 merged 1 commit into
NVIDIA:mainfrom
brnguyen2:k3/15177-wire-moe-unit-tests

Conversation

@brnguyen2

@brnguyen2 brnguyen2 commented Aug 14, 2026

Copy link
Copy Markdown
Collaborator

Description

Three Kimi K3 MoE unit tests exist in the tree but are referenced by no L0
test list, so they never run in pre-merge CI:

  • tests/unittest/_torch/modules/moe/test_kimi_k3_mlp.py
  • tests/unittest/_torch/modules/moe/test_kimi_k3_moe_gate.py
  • tests/unittest/_torch/modules/moe/test_kimi_k3_situ_and_mul.py

All three are any-CUDA: they exercise the Triton trtllm::situ_and_mul op and
the noaux_tc_op routing op against a torch reference, gated on requires_cuda
only (not SM100/SM103). They are wired into l0_h100.yml (pre-merge, single-GPU)
next to the other MoE-component unit tests, so they add coverage on Hopper
rather than consuming scarce Blackwell pre-merge capacity.

The Blackwell-gated K3 suites (kimi_kda, kimi_k3_attn_res,
kimi_k3_situ_moe, KDA parity) are already wired in l0_b200.yml and
l0_gb300_multi_gpus.yml (landed under this ticket in #17413); this fills the
last gap for the any-CUDA K3 MoE files. Addresses item 1.4 of TRTLLM-15177.

Test-list-only change — no source/API changes.

Test Coverage

The three added entries are the tests themselves. Validated with the repo's
own checker:

python3 scripts/check_test_list.py --validate
# OK: 2051 unique test entries validated.

(also runs as the "Validate test list entries exist in source files (AST)"
pre-commit hook, which passed on commit.)

PR Checklist

  • Please check this after reviewing the above items as appropriate for this PR.

Dev Engineer Review

  • Added three CUDA-gated Kimi K3 MoE tests to tests/integration/test_lists/test-db/l0_h100.yml.
  • Added entries:
    • test_kimi_k3_mlp.py
    • test_kimi_k3_moe_gate.py
    • test_kimi_k3_situ_and_mul.py
  • The entries match the H100 pre-merge test scope.
  • Test-list validation passed with 2,051 unique entries.
  • No source, API, or public entity changes were made.

QA Engineer Review

  • Modified tests/integration/test_lists/test-db/l0_h100.yml.
  • Added three Kimi K3 MoE test suites.
  • Removed no entries.
  • Verdict: needs follow-up because CBTS coverage data is unavailable.

…opper)

test_kimi_k3_mlp.py, test_kimi_k3_moe_gate.py, and test_kimi_k3_situ_and_mul.py
existed in the tree but were referenced by no L0 test list, so they never ran
in pre-merge CI.

They are any-CUDA (Triton trtllm::situ_and_mul op plus a torch reference, gated
on requires_cuda only, not SM100/SM103), so wire them into the H100 pre-merge
single-GPU list next to the other MoE-component unit tests rather than spend
scarce Blackwell capacity. The Blackwell-gated K3 suites (kimi_kda,
kimi_k3_attn_res, kimi_k3_situ_moe, KDA parity) are already wired in l0_b200.yml
and l0_gb300_multi_gpus.yml.

Closes item 1.4 of TRTLLM-15177 for the previously-unwired K3 MoE files.

Signed-off-by: Brian Nguyen <brnguyen@nvidia.com>
@brnguyen2
brnguyen2 marked this pull request as ready for review August 14, 2026 15:14
@brnguyen2
brnguyen2 requested review from a team as code owners August 14, 2026 15:14
@brnguyen2

Copy link
Copy Markdown
Collaborator Author

/bot run

@coderabbitai

coderabbitai Bot commented Aug 14, 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: 2876f944-15c3-4194-a7d8-a9e1bd8f9b57

📥 Commits

Reviewing files that changed from the base of the PR and between 8d8f81a and ef5c8ab.

📒 Files selected for processing (1)
  • tests/integration/test_lists/test-db/l0_h100.yml

Walkthrough

The H100 PyTorch MPI pre-merge test list now includes Kimi K3 MoE unit tests for the MLP, MoE gate, and situ_and_mul components.

Changes

Kimi K3 MoE Test Coverage

Layer / File(s) Summary
Enable Kimi K3 MoE unit tests
tests/integration/test_lists/test-db/l0_h100.yml
Adds the Kimi K3 MoE test section to the H100 pre-merge suite and enables tests for the MLP, MoE gate, and situ_and_mul implementations.

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

Merge Risk: 🟡 Moderate · up to ef5c8

This change only adds three existing CUDA unit tests to the Hopper pre-merge list, with no product-code changes. It is not merge-ready until the required coverage-scope verdict is supplied or explicitly accepted.

Suggested reviewers: bowenfu

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly identifies the ticket, test change, Kimi K3 MoE scope, and Hopper L0 target.
Description check ✅ Passed The description explains the issue, lists the affected tests, documents test-list validation, and confirms the checklist review.
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 #66303 [ run ] triggered by Bot. Commit: ef5c8ab Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #66303 [ run ] completed with state SUCCESS. Commit: ef5c8ab
/LLM/main/L0_MergeRequest_PR pipeline #53958 completed with status: 'SUCCESS'

CI Report

Link to invocation

@brnguyen2
brnguyen2 merged commit 43d14ef into NVIDIA:main Aug 16, 2026
13 checks passed
xinhe-nv pushed a commit to xinhe-nv/TensorRT-LLM that referenced this pull request Aug 17, 2026
…opper) (NVIDIA#17711)

Signed-off-by: Brian Nguyen <brnguyen@nvidia.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.

4 participants