[TRTLLM-17005][refactor] Component-local C++ Tests (Part 3a) by Funatiq · Pull Request #21022 · NVIDIA/TensorRT-LLM

Funatiq · 2026-10-26T12:15:27Z

Dev Engineer Review

The change extracts selected kernels into static component libraries and links them into tensorrt_llm with whole-archive semantics. It also updates CUTLASS and FMHA dependencies, source discovery, and kernel-test target wiring. The FMHA custom-mask archive remains a private implementation dependency. The supplied information does not establish test results for this source state.

Review findings and severity counts are unavailable. CI reports failures for builds 66367, 66380, 66394, and 66423, and an unstable result for build 66548. The comments do not identify specific failing tests.

QA Engineer Review

cpp/tests/unit_tests/kernels/CMakeLists.txt migrates kernel test targets to add_tllm_gtest with explicit owners, dependencies, source files, and labels. The registrations cover logits, NVFP4 cold-page, attention masks, RoPE and shift-K-cache, MLA, chunked prefill, sparse attention, MoE communication, load balancing, conditional MoE LoRA, and sparse KV cache. The NVFP4 cold-page test now links reusable component libraries instead of listing support sources and link settings directly.

Changed test functions and IDs are not identified in the supplied information. No changes to tests/integration/test_lists/ are reported, so CI or manual-QA listing status cannot be established. Coverage verdict: needs follow-up. The supplied CI summary reports failures and an unstable pipeline, but does not identify specific failing tests.

Per-File QA Perspective

cpp/tensorrt_llm/CMakeLists.txt: Whole-archive links retain component kernels in the shared library. Verify that each registered component is linked correctly.
cpp/tensorrt_llm/kernels/CMakeLists.txt: Propagates the component target list to the parent scope. Verify that consumers receive the complete list.
cpp/tensorrt_llm/kernels/cutlass_kernels/CMakeLists.txt: Changes LoRA source discovery and links the LoRA component when OSS MoE GEMM is enabled. Verify both conditional paths.
cpp/tensorrt_llm/kernels/kernelComponents.cmake: Adds static component-library registration, source removal, and conditional MoE LoRA registration. Verify source ownership and dependency configuration.
cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/CMakeLists.txt: Excludes prepareCustomMask.cu from recursive discovery and privately links the attention-mask component. Verify custom-mask behavior and source ownership.
cpp/tests/unit_tests/kernels/CMakeLists.txt: Migrates kernel test targets and replaces manually listed NVFP4 support sources with component libraries. Verify dependencies, labels, and conditional MoE LoRA registration.

Description

Implement component-local tests as real CMake target dependencies. This PR migrates some of the kernel tests.

Extracts 10 kernel families into dedicated static libraries, covering logits, NVFP4 cold pages, RoPE/QKV preprocessing, sparse attention, MLA, MoE communication/load balancing/LoRA, and custom attention masks.
Migrates 14 test executables to add_tllm_gtest, with explicit component dependencies, ownership, and scheduling labels. This reduces their dependency on the full TensorRT-LLM library.
Keeps the extracted kernels included in the main shared library through whole-archive linking and updates CUTLASS/FМHA dependencies to avoid duplicate compilation.
Replaces the NVFP4 test’s manually assembled support sources with reusable component libraries.
Removes GPU resource locks introduced during the migration.

All committed changes are CMake build/test wiring; kernel implementations and test bodies are unchanged.

Test Coverage

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.

Funatiq · 2026-10-26T12:15:35Z

/bot run

tensorrt-cicd · 2026-10-26T12:22:47Z

PR_Github #80609 [ run ] triggered by Bot. Commit: 66f2c7f Link to invocation

tensorrt-cicd · 2026-10-26T12:52:43Z

PR_Github #80609 [ run ] completed with state FAILURE. Commit: 66f2c7f
/LLM/main/L0_MergeRequest_PR pipeline #66367 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

Funatiq · 2026-10-26T14:57:39Z

/bot run

tensorrt-cicd · 2026-10-26T15:07:01Z

PR_Github #80625 [ run ] triggered by Bot. Commit: 6067e22 Link to invocation

tensorrt-cicd · 2026-10-26T15:38:41Z

PR_Github #80625 [ run ] completed with state FAILURE. Commit: 6067e22
/LLM/main/L0_MergeRequest_PR pipeline #66380 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

Funatiq · 2026-10-26T16:02:49Z

/bot run

tensorrt-cicd · 2026-10-26T16:09:17Z

PR_Github #80642 [ run ] triggered by Bot. Commit: e144d1b Link to invocation

tensorrt-cicd · 2026-10-26T17:53:06Z

PR_Github #80642 [ run ] completed with state SUCCESS. Commit: e144d1b
/LLM/main/L0_MergeRequest_PR pipeline #66394 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

Funatiq · 2026-10-26T18:36:50Z

/bot run

tensorrt-cicd · 2026-10-26T18:45:20Z

PR_Github #80671 [ run ] triggered by Bot. Commit: 9a8e8fd Link to invocation

tensorrt-cicd · 2026-10-26T23:29:32Z

PR_Github #80671 [ run ] completed with state SUCCESS. Commit: 9a8e8fd
/LLM/main/L0_MergeRequest_PR pipeline #66423 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

Funatiq · 2026-10-27T05:35:42Z

/bot run

tensorrt-cicd · 2026-10-27T05:46:01Z

PR_Github #80816 [ run ] triggered by Bot. Commit: 9a8e8fd Link to invocation

tensorrt-cicd · 2026-10-27T08:36:57Z

PR_Github #80816 [ run ] completed with state SUCCESS. Commit: 9a8e8fd
/LLM/main/L0_MergeRequest_PR pipeline #66548 completed with status: 'UNSTABLE'

CI Report

⚠️ Multi-GPU Label Required:
Multi-GPU tests require the ci: full pre-merge approved label on this PR. Either:

Wait for the PR to be fully approved — the label is added automatically once approval is complete. Having unresolved open comments is fine, or
If needed, ask a member of NVIDIA/trt-llm-ci-approvers to add the label manually.
Then re-trigger CI with the same bot command (no rebase needed).

⚠️ 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

Link to invocation

coderabbitai · 2026-10-27T08:56:05Z

Important

Review skipped

Review was skipped as selected files did not have any reviewable changes.

Run configuration

Source mode: Auto
Repository: NVIDIA/TensorRT-LLM
Branch: main
File: .coderabbit.yaml
Commit: 0cd0a18
Layers: Repository YAML
Review profile: CHILL
Plan: Enterprise
Run ID: 86b98480-ce24-4b03-a4ce-3db12d554b8b

Commits

Reviewing files that changed from the base of the PR and between 73d65ca and 14479fb.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

🔍 Trigger review

No actionable comments were generated in the recent review.

Recent review info

Run configuration

Source mode: Auto
Repository: NVIDIA/TensorRT-LLM
Branch: main
File: .coderabbit.yaml
Commit: 64c1ce1
Layers: Repository YAML
Review profile: CHILL
Plan: Enterprise
Run ID: 7a5a9be3-1cff-40f4-810e-8b657c6e9412

Commits

Reviewing files that changed from the base of the PR and between 9a8e8fd and 73d65ca.

Files selected for processing: 3

cpp/tensorrt_llm/kernels/kernelComponents.cmake
cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/CMakeLists.txt
cpp/tests/unit_tests/kernels/CMakeLists.txt

Included review availability: This review used your included allowance. Your plan provides up to 12 included reviews per hour; 11 remain after this review.

Walkthrough

The build now defines kernel component libraries, connects them to the shared target, and updates FMHA and MoE source wiring. Kernel unit-test declarations now use add_tllm_gtest with explicit owners, sources, dependencies, and labels.

Changes

Kernel component build

Layer / File(s)	Summary
Define kernel component libraries `cpp/tensorrt_llm/kernels/kernelComponents.cmake`	A new CMake helper validates arguments, creates static kernel libraries and namespaced aliases, and registers component targets with their sources and dependencies.
Wire component libraries into kernel sources `cpp/tensorrt_llm/kernels/cutlass_kernels/CMakeLists.txt`, `cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/CMakeLists.txt`	The MoE and FMHA source lists exclude files handled by component libraries and link the corresponding targets. `MOE_CUTLASS_DIR` is converted to an absolute path.
Propagate and link kernel components `cpp/tensorrt_llm/kernels/CMakeLists.txt`, `cpp/tensorrt_llm/CMakeLists.txt`	The kernel directory propagates component targets to its parent. The shared target links each component with `WHOLE_ARCHIVE` and sets its link-library override accordingly.
Migrate kernel test declarations `cpp/tests/unit_tests/kernels/CMakeLists.txt`	Kernel tests use `add_tllm_gtest` declarations with explicit owners, sources, dependencies, and labels. The NVFP4 cold-page test links the kernel and KV-cache host-memory libraries.

Priority: Low

Estimated code review effort: 3 (Moderate) | ~25 minutes

Suggested reviewers: qijune

Merge Risk: Minimal · previous review 73d65

No concrete build or test-wiring defect is established by the reviewed changes; reported CI failures still need their individual causes identified through normal validation.

Pre-merge checks: 5

Check name	Status	Explanation
Title check		The title clearly identifies the ticket, change type, and main change: migrating component-local C++ tests.
Description check		The description clearly explains the CMake and test-wiring changes and includes the required sections and checklist. The Test Coverage section is empty and does not list specific tests or commands, bu…
Docstring Coverage		No eligible functions found in the changed files. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Documentation-only edits and deletions within survi…
Linked Issues check		Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check		Check skipped because no linked issues were found for this pull request.

Full details: Description check

Explanation

The description clearly explains the CMake and test-wiring changes and includes the required sections and checklist. The Test Coverage section is empty and does not list specific tests or commands, but the overall description is sufficiently complete.

Full details: Docstring Coverage

Explanation

No eligible functions found in the changed files. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Documentation-only edits and deletions within surviving functions are included; unchanged diff context and fully deleted functions are excluded. Analyzed 0 functions across 0 files. (3 skipped: 3 unsupported.)

Finishing Touches

🧪 Generate unit tests (beta)

Create a new PR

Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

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

yuxianq · 2026-10-27T09:06:17Z

@farazkh80, could you help to review this PR as trt-llm-torch-attention-devs? Thanks~

Assignment explanation

Components	integration/build-config (100%)
Tags	features:custom-mask (100%)
PR effort	3 points — The small CMake refactor requires checking that the component dependency preserves custom-mask symbols and avoids duplicate compilation. Missing dependency definitions make this more demanding than a mechanical edit.
Affinity (0–1)	0.500 component/tag match
Outstanding points at selection	3 → 6 (+3)
Points already reserved on this PR	0
Effective weight	1
Completed review points (preceding 168 hours)	65
Combined points after assignment	71
Demand-derived target	61.00 points (soft share)
Additional fair share before assignment	0.00 points
Share explanation	Whole PR / qualification or coverage constraint exceeds a soft share; assignment is allowed.
Selection rule	balance-first maintenance
Assignment scope (farazkh80)	all

Affinity and workload are snapshots at selection, not live counters. Existing reservations on this PR are counted once.

Keep the FMHA interface public while making the custom-mask kernel archive an implementation dependency. The shared library already retains the archive through its private whole-archive component linkage, so downstream consumers do not need it in the public link interface. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

Funatiq · 2026-10-28T10:46:17Z

/bot run

tensorrt-cicd · 2026-10-28T10:53:16Z

PR_Github #81169 [ run ] triggered by Bot. Commit: 14479fb Link to invocation

tensorrt-cicd · 2026-10-28T13:47:45Z

PR_Github #81169 [ run ] completed with state SUCCESS. Commit: 14479fb
/LLM/main/L0_MergeRequest_PR pipeline #66864 completed with status: 'FAILURE'

CI Report

⚠️ Resource Maintenance — Test Coverage Reduced:

Resource maintenance in LLM/main/L0_Test-x86_64-Single-GPU #9590: L40S-PyTorch-2 is temporarily paused due to Kubernetes agent provisioning and node issues.
Affected stages:
L40S-PyTorch-2

⚠️ 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

Funatiq · 2026-10-28T13:51:05Z

/bot run

tensorrt-cicd · 2026-10-28T13:59:20Z

PR_Github #81185 [ run ] triggered by Bot. Commit: 14479fb Link to invocation

tensorrt-cicd · 2026-10-28T16:45:35Z

PR_Github #81185 [ run ] completed with state SUCCESS. Commit: 14479fb
/LLM/main/L0_MergeRequest_PR pipeline #66879 completed with status: 'FAILURE'

CI Report

⚠️ Resource Maintenance — Test Coverage Reduced:

Resource maintenance in LLM/main/L0_Test-x86_64-Single-GPU #9103: L40S-PyTorch-2 is temporarily paused due to Kubernetes agent provisioning and node issues.
Affected stages:
L40S-PyTorch-2

⚠️ 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

brnguyen2

Approving — the comments below are optional touch-ups, not blockers.

Moving each test onto add_tllm_gtest with a narrow LINK_LIBRARIES list is a clear improvement. The nvfp4 cold-page test in particular no longer carries its hand-maintained list of common/*.cpp and kv_cache_manager_v2/utils/*.cpp sources.

Two things before merge:

CI status: the PR history shows several failed or unstable pipelines. Please post a green /bot run on the current head. This change moves sources between link units, so only a full build plus the migrated kernels ctest labels can show that nothing went missing or got duplicated in libtensorrt_llm.so.
Description: the PR description is cut off partway through the list of extracted families ("MoE communication/loa…"). Please complete it, and say what "Part 3a" covers compared with the later parts, so a future reader can tell which kernel tests are still on add_gtest and why.

github-actions · 2026-10-28T17:40:43Z

Automatically added "ci: full pre-merge approved" because this PR has satisfied the required GitHub review approvals. Unresolved review conversations and other required checks remain independent merge requirements.

Funatiq · 2026-10-28T17:43:25Z

/bot run

tensorrt-cicd · 2026-10-28T17:49:53Z

PR_Github #81219 [ run ] triggered by Bot. Commit: 14479fb Link to invocation

tensorrt-cicd · 2026-10-28T20:27:47Z

PR_Github #81219 [ run ] completed with state FAILURE. Commit: 14479fb
/LLM/main/L0_MergeRequest_PR pipeline #66910 completed with status: 'FAILURE'

CI Report

⚠️ Resource Maintenance — Test Coverage Reduced:

Resource maintenance in LLM/main/L0_Test-x86_64-Single-GPU #10088: L40S-PyTorch-2 is temporarily paused due to Kubernetes agent provisioning and node issues.
Affected stages:
L40S-PyTorch-2

⚠️ 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

Funatiq · 2026-10-28T21:06:31Z

/bot run

tensorrt-cicd · 2026-10-28T21:13:39Z

PR_Github #81255 [ run ] triggered by Bot. Commit: 14479fb Link to invocation

tensorrt-cicd · 2026-10-28T23:21:18Z

PR_Github #81255 [ run ] completed with state SUCCESS. Commit: 14479fb
/LLM/main/L0_MergeRequest_PR pipeline #66944 completed with status: 'FAILURE'

CI Report

⚠️ Resource Maintenance — Test Coverage Reduced:

Resource maintenance in LLM/main/L0_Test-x86_64-Single-GPU #9613: L40S-PyTorch-2 is temporarily paused due to Kubernetes agent provisioning and node issues.
Affected stages:
L40S-PyTorch-2

⚠️ 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

Funatiq · 2026-10-29T04:24:23Z

/bot run

tensorrt-cicd · 2026-10-29T04:31:21Z

PR_Github #81337 [ run ] triggered by Bot. Commit: 14479fb Link to invocation

tensorrt-cicd · 2026-10-29T05:24:30Z

PR_Github #81337 [ run ] completed with state FAILURE. Commit: 14479fb
/LLM/main/L0_MergeRequest_PR pipeline #67020 completed with status: 'FAILURE'

CI Report

⚠️ Resource Maintenance — Test Coverage Reduced:

Resource maintenance in LLM/main/L0_Test-x86_64-Single-GPU #9637: L40S-PyTorch-2 is temporarily paused due to Kubernetes agent provisioning and node issues.
Affected stages:
L40S-PyTorch-2

⚠️ 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

Funatiq · 2026-10-29T07:39:51Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-10-29T07:47:33Z

PR_Github #81389 [ run ] triggered by Bot. Commit: 14479fb Link to invocation

tensorrt-cicd · 2026-10-29T10:10:01Z

PR_Github #81389 [ run ] completed with state SUCCESS. Commit: 14479fb
/LLM/main/L0_MergeRequest_PR pipeline #67064 completed with status: 'SUCCESS'

CI Report

Link to invocation

….3: Restore Mistral Large 3 multimodal inference Forward-port of release/1.3 PR NVIDIA#19788 (release/1.3 commit 48c796c) to main. Adapted to main: adopts main's MultimodalItemMetadata contract from _build_mm_item_metadata and exposes it through get_mm_item_metadata, and the new tests call get_mm_item_metadata and compare against the tuples that MultimodalItemMetadata now stores. Also: the HF tokenizer load in MistralHFInputProcessor follows the trust_remote_code argument like the processor load next to it, and build_fmha_head104_tests requests dynamic NVRTC linking and passes plain architecture numbers (NVIDIA#20137) like the other configure-only gtest fixtures, so the target does not depend on a configure cache left by an earlier fixture. It also regenerates the FMHA sources, so a stale generation stamp cannot hide the head-104 generator changes, and fmhaHead104Test is registered with add_tllm_gtest (OWNER, LABELS, FULL_STACK) as main asks for new C++ tests (NVIDIA#21022). Signed-off-by: Pranav Shrestha <254760092+pranav-nvidia@users.noreply.github.com> Co-authored-by: Pranav Shrestha <254760092+pranav-nvidia@users.noreply.github.com> Signed-off-by: Simeng Liu <simengl@nvidia.com>

github-actions Bot assigned Funatiq Oct 26, 2026

Funatiq force-pushed the dev/refactor/component-local-tests-3-a branch from 66f2c7f to 6067e22 Compare October 26, 2026 14:57

Funatiq force-pushed the dev/refactor/component-local-tests-3-a branch from 6067e22 to e144d1b Compare October 26, 2026 16:02

Funatiq force-pushed the dev/refactor/component-local-tests-3-a branch from e144d1b to 9a8e8fd Compare October 26, 2026 18:36

Funatiq marked this pull request as ready for review October 27, 2026 08:50

Funatiq requested review from a team as code owners October 27, 2026 08:50

Funatiq requested review from brnguyen2, lfr-0531, pengbowang-nv, schetlur-nv and zongfeijing October 27, 2026 08:50

Funatiq force-pushed the dev/refactor/component-local-tests-3-a branch from 73d65ca to 14479fb Compare October 28, 2026 10:46

brnguyen2 approved these changes Oct 28, 2026

View reviewed changes

Comment thread cpp/tensorrt_llm/kernels/kernelComponents.cmake Resolved

trtllm-agent added the ci: full pre-merge approved label Oct 28, 2026

Funatiq merged commit e655dd8 into NVIDIA:main Oct 29, 2026
14 checks passed

Funatiq deleted the dev/refactor/component-local-tests-3-a branch October 29, 2026 10:16

SimengLiu-nv mentioned this pull request Nov 2, 2026

[None][chore] Mass merge release/1.3 branch back to main (batch 2) #20843

Merged

1 task done

Conversation

Funatiq commented Oct 26, 2026 • edited by coderabbitai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Dev Engineer Review

QA Engineer Review

Per-File QA Perspective

Description

Test Coverage

PR Checklist

GitHub Bot Help

Uh oh!

Funatiq commented Oct 26, 2026

Uh oh!

tensorrt-cicd commented Oct 26, 2026

Uh oh!

tensorrt-cicd commented Oct 26, 2026

Uh oh!

Funatiq commented Oct 26, 2026

Uh oh!

tensorrt-cicd commented Oct 26, 2026

Uh oh!

tensorrt-cicd commented Oct 26, 2026

Uh oh!

Funatiq commented Oct 26, 2026

Uh oh!

tensorrt-cicd commented Oct 26, 2026

Uh oh!

tensorrt-cicd commented Oct 26, 2026

Uh oh!

Funatiq commented Oct 26, 2026

Uh oh!

tensorrt-cicd commented Oct 26, 2026

Uh oh!

tensorrt-cicd commented Oct 26, 2026

Uh oh!

Funatiq commented Oct 27, 2026

Uh oh!

tensorrt-cicd commented Oct 27, 2026

Uh oh!

tensorrt-cicd commented Oct 27, 2026

Uh oh!

coderabbitai Bot commented Oct 27, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Review skipped

Walkthrough

Changes

Uh oh!

yuxianq commented Oct 27, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Funatiq commented Oct 28, 2026

Uh oh!

tensorrt-cicd commented Oct 28, 2026

Uh oh!

tensorrt-cicd commented Oct 28, 2026

Uh oh!

Funatiq commented Oct 28, 2026

Uh oh!

tensorrt-cicd commented Oct 28, 2026

Uh oh!

tensorrt-cicd commented Oct 28, 2026

Uh oh!

brnguyen2 left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

github-actions Bot commented Oct 28, 2026

Uh oh!

Funatiq commented Oct 28, 2026

Uh oh!

tensorrt-cicd commented Oct 28, 2026

Uh oh!

tensorrt-cicd commented Oct 28, 2026

Uh oh!

Funatiq commented Oct 28, 2026

Uh oh!

tensorrt-cicd commented Oct 28, 2026

Uh oh!

tensorrt-cicd commented Oct 28, 2026

Uh oh!

Funatiq commented Oct 26, 2026 •

edited by coderabbitai Bot

Loading

coderabbitai Bot commented Oct 27, 2026 •

edited

Loading

yuxianq commented Oct 27, 2026 •

edited

Loading