[TRTLLM-13639][test] Migrate Kimi dis-agg tests to Transceiver v2 and trim tests by Shixiaowei02 · Pull Request #16482 · NVIDIA/TensorRT-LLM

Shixiaowei02 · 2026-07-16T07:07:58Z

Description

This pull request removes the TestKimiK2 disaggregated serving test and updates the TestKimiK25 test to use the NIXL Python (v2) cache transceiver instead of the default backend. The test list is also updated to reflect the removal of the Kimi-K2 test. These changes streamline the test suite and ensure the Kimi-K2.5 test uses the latest cache transceiver configuration.

Test removals:

Removed the TestKimiK2 class and its test_nvfp4 method from test_disaggregated_serving.py, which tested the Kimi-K2 model in a disaggregated serving setup.
Removed the corresponding TestKimiK2::test_nvfp4 entry from the test list in qa/llm_function_core.txt.

Test configuration updates:

Updated the TestKimiK25.test_nvfp4 method to use the NIXL backend with PYTHON transceiver runtime for both context and generation servers, replacing the previous DEFAULT backend. [1] [2]
Clarified the test docstring to indicate the use of the NIXL Python (v2) cache transceiver.

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.

Summary by CodeRabbit

Tests
- Updated NVFP4 accuracy coverage for the Kimi K2.5 model.
- Refined GB200 and GB300 performance scenarios to emphasize key large-context configurations.
- Improved disaggregated serving test coverage with explicit runtime and resource limits.
- Removed outdated or redundant benchmark scenarios, including legacy UCX-based configurations.
- Expanded performance validation for selected Kimi K2.5 and DeepSeek model variants.

Shixiaowei02 · 2026-07-16T07:25:03Z

/bot run --disable-fail-fast

coderabbitai · 2026-07-16T07:26:52Z

📝 Walkthrough

Walkthrough

Replaces the Kimi-K2 NVFP4 accuracy test with Kimi-K2.5 coverage, updates disaggregated performance selections, removes obsolete benchmark variants, and explicitly configures the Python runtime for selected NIXL transceivers.

Changes

Kimi-K2.5 disaggregated serving

Layer / File(s)	Summary
Kimi-K2.5 accuracy test `tests/integration/defs/accuracy/test_disaggregated_serving.py`, `tests/integration/test_lists/qa/llm_function_core.txt`	Replaces `TestKimiK2` with `TestKimiK25`, updates model and server limits, and configures both context and generation servers with NIXL and the Python transceiver runtime.
Performance test selection `tests/integration/test_lists/qa/`, `tests/integration/test_lists/test-db/`	Removes obsolete Kimi context, UCX, and small-concurrency variants while retaining or adding selected Kimi-K2.5 NIXL and DeepSeek cases across GB200 and GB300 matrices.
Benchmark transceiver runtime `tests/scripts/perf/disaggregated/gb200_kimi-k25-thinking-fp4_.yaml`, `tests/scripts/perf/disaggregated/gb300_kimi-k25-thinking-fp4_.yaml`	Adds `transceiver_runtime: PYTHON` to generation and context NIXL cache-transceiver configurations.

Estimated code review effort: 3 (Moderate) | ~20 minutes

Possibly related PRs

NVIDIA/TensorRT-LLM#16355: Adds Python transceiver runtime settings to related disaggregated performance configurations.
NVIDIA/TensorRT-LLM#16390: Switches disaggregated serving context and generation servers from DEFAULT to NIXL with the Python runtime.

Suggested reviewers: fredricz-20070104

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
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.
Title check	✅ Passed	The title clearly summarizes the main change: migrating Kimi disaggregated tests to NIXL v2 and trimming redundant tests.
Description check	✅ Passed	The description follows the template with a clear summary and checklist, but the Test Coverage section is left empty.

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests

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

coderabbitai

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@tests/integration/defs/accuracy/test_disaggregated_serving.py`:
- Around line 2233-2234: Update the test description/docstring associated with
the configurations near the NIXL backend and PYTHON transceiver_runtime entries
to state that both roles explicitly use NIXL with the Python runtime, rather
than the default transceiver. Apply the same wording update to the additional
location noted in the review.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

Push a commit to this branch (recommended)
Create a new PR with the fixes

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: aeb230f1-3914-445e-a075-d9339380429a

📥 Commits

Reviewing files that changed from the base of the PR and between 44f0521 and 853df7a.

📒 Files selected for processing (26)

tests/integration/defs/accuracy/test_disaggregated_serving.py
tests/integration/test_lists/qa/llm_function_core.txt
tests/integration/test_lists/qa/llm_perf_disagg.yml
tests/integration/test_lists/qa/llm_perf_multinode.txt
tests/integration/test_lists/test-db/l0_gb200_multi_gpus_perf_sanity.yml
tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node1_gpu4.yml
tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node2_gpu8.yml
tests/integration/test_lists/test-db/l0_gb300_multi_gpus_perf_sanity.yml
tests/integration/test_lists/test-db/l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node1_gpu4.yml
tests/integration/test_lists/test-db/l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node2_gpu8.yml
tests/scripts/perf/disaggregated/gb200_kimi-k25-thinking-fp4_1k1k_con2048_ctx1_dep4_gen1_dep32_eplb0_mtp0_ccb-NIXL.yaml
tests/scripts/perf/disaggregated/gb200_kimi-k25-thinking-fp4_1k1k_con4096_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-NIXL.yaml
tests/scripts/perf/disaggregated/gb200_kimi-k25-thinking-fp4_1k1k_con4096_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-UCX.yaml
tests/scripts/perf/disaggregated/gb200_kimi-k25-thinking-fp4_1k1k_con4_ctx1_dep4_gen1_tep4_eplb0_mtp0_ccb-NIXL.yaml
tests/scripts/perf/disaggregated/gb200_kimi-k25-thinking-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb416_mtp3_ccb-NIXL.yaml
tests/scripts/perf/disaggregated/gb200_kimi-k25-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp0_ccb-NIXL.yaml
tests/scripts/perf/disaggregated/gb200_kimi-k25-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp0_ccb-UCX.yaml
tests/scripts/perf/disaggregated/gb200_kimi-k25-thinking-fp4_8k1k_con4_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-NIXL.yaml
tests/scripts/perf/disaggregated/gb300_kimi-k25-thinking-fp4_1k1k_con2048_ctx1_dep4_gen1_dep32_eplb0_mtp0_ccb-NIXL.yaml
tests/scripts/perf/disaggregated/gb300_kimi-k25-thinking-fp4_1k1k_con4096_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-NIXL.yaml
tests/scripts/perf/disaggregated/gb300_kimi-k25-thinking-fp4_1k1k_con4096_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-UCX.yaml
tests/scripts/perf/disaggregated/gb300_kimi-k25-thinking-fp4_1k1k_con4_ctx1_dep4_gen1_tep4_eplb0_mtp0_ccb-NIXL.yaml
tests/scripts/perf/disaggregated/gb300_kimi-k25-thinking-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb416_mtp3_ccb-NIXL.yaml
tests/scripts/perf/disaggregated/gb300_kimi-k25-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp0_ccb-NIXL.yaml
tests/scripts/perf/disaggregated/gb300_kimi-k25-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp0_ccb-UCX.yaml
tests/scripts/perf/disaggregated/gb300_kimi-k25-thinking-fp4_8k1k_con4_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-NIXL.yaml

💤 Files with no reviewable changes (16)

tests/integration/test_lists/test-db/l0_gb300_multi_gpus_perf_sanity.yml
tests/scripts/perf/disaggregated/gb200_kimi-k25-thinking-fp4_1k1k_con4_ctx1_dep4_gen1_tep4_eplb0_mtp0_ccb-NIXL.yaml
tests/scripts/perf/disaggregated/gb200_kimi-k25-thinking-fp4_8k1k_con4_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-NIXL.yaml
tests/scripts/perf/disaggregated/gb300_kimi-k25-thinking-fp4_1k1k_con4_ctx1_dep4_gen1_tep4_eplb0_mtp0_ccb-NIXL.yaml
tests/scripts/perf/disaggregated/gb300_kimi-k25-thinking-fp4_1k1k_con4096_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-UCX.yaml
tests/scripts/perf/disaggregated/gb300_kimi-k25-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp0_ccb-UCX.yaml
tests/scripts/perf/disaggregated/gb200_kimi-k25-thinking-fp4_1k1k_con4096_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-UCX.yaml
tests/scripts/perf/disaggregated/gb200_kimi-k25-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp0_ccb-UCX.yaml
tests/integration/test_lists/qa/llm_function_core.txt
tests/scripts/perf/disaggregated/gb300_kimi-k25-thinking-fp4_8k1k_con4_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-NIXL.yaml
tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node2_gpu8.yml
tests/integration/test_lists/test-db/l0_gb200_multi_gpus_perf_sanity.yml
tests/integration/test_lists/test-db/l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node2_gpu8.yml
tests/integration/test_lists/test-db/l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node1_gpu4.yml
tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node1_gpu4.yml
tests/integration/test_lists/qa/llm_perf_multinode.txt

tensorrt-cicd · 2026-07-16T07:30:47Z

PR_Github #59657 [ run ] triggered by Bot. Commit: 853df7a Link to invocation

Shixiaowei02 · 2026-07-16T07:43:48Z

/bot run --stage-list "DGX_B200-8_GPUs-PyTorch-1,DGX_B200-8_GPUs-PyTorch-2,DGX_B200-8_GPUs-PyTorch-3,DGX_B200-8_GPUs-PyTorch-4"

Shixiaowei02 · 2026-07-16T07:45:31Z

/bot kill

tensorrt-cicd · 2026-07-16T07:49:48Z

PR_Github #59662 [ run ] triggered by Bot. Commit: ef95e3a Link to invocation

tensorrt-cicd · 2026-07-16T07:52:19Z

PR_Github #59664 [ kill ] triggered by Bot. Commit: ef95e3a Link to invocation

tensorrt-cicd · 2026-07-16T07:53:28Z

PR_Github #59657 [ run ] completed with state ABORTED. Commit: 853df7a

Link to invocation

Shixiaowei02 · 2026-07-20T02:29:19Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-07-20T02:34:59Z

PR_Github #60221 [ run ] triggered by Bot. Commit: bc28173 Link to invocation

Mirror the GPT-OSS approach (NVIDIA#16479): KimiK25ForConditionalGeneration now declares "PYTHON" as its preferred KV-cache transceiver runtime, so disaggregated Kimi-K2.5 adopts the Python (v2) transceiver by default when the user leaves transceiver_runtime at 'auto' and the effective backend is NIXL. Explicit user settings and non-NIXL backends are unaffected. - modeling_kimi_k25.py: add get_preferred_transceiver_runtime() -> "PYTHON". - test_modeling_kimi_k25.py: unit test asserting the preference. - TestKimiK25::test_nvfp4: set cache_transceiver_config explicitly to backend=NIXL + transceiver_runtime=PYTHON (ctx and gen). The disagg test harness injects TRTLLM_USE_UCX_KVCACHE=1 for any non-NIXL backend, so a "DEFAULT" backend would resolve to UCX and force the C++ transceiver; the test sets NIXL explicitly so it actually exercises the Python transceiver rather than relying on the model-default resolution. - Remove the redundant TestKimiK2::test_nvfp4 disaggregated accuracy test; Kimi disaggregated accuracy is covered by TestKimiK25, and Kimi-K2-Thinking accuracy stays covered by the aggregated tests in test_llm_api_pytorch. Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>

Shixiaowei02 · 2026-07-20T02:58:07Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-07-20T03:01:38Z

PR_Github #60221 [ run ] completed with state FAILURE. Commit: bc28173
/LLM/main/L0_MergeRequest_PR pipeline #48589 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

tensorrt-cicd · 2026-07-20T03:04:07Z

PR_Github #60233 [ run ] triggered by Bot. Commit: 0089eeb Link to invocation

tensorrt-cicd · 2026-07-20T07:50:50Z

PR_Github #60233 [ run ] completed with state SUCCESS. Commit: 0089eeb
/LLM/main/L0_MergeRequest_PR pipeline #48599 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

Shixiaowei02 · 2026-07-20T10:35:01Z

/bot run --disable-fail-fast --stage-list "GH200-PackageSanityCheck-PY312-UB2404, A10-PyTorch-1, B300-PyTorch-1, H100_PCIe-AutoDeploy-1"

tensorrt-cicd · 2026-07-20T10:40:46Z

PR_Github #60354 [ run ] triggered by Bot. Commit: 0089eeb Link to invocation

tensorrt-cicd · 2026-07-20T12:40:11Z

PR_Github #60354 [ run ] completed with state SUCCESS. Commit: 0089eeb
/LLM/main/L0_MergeRequest_PR pipeline #48697 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

Shixiaowei02 · 2026-07-20T16:03:14Z

/bot run --disable-fail-fast --only-multi-gpu-test

tensorrt-cicd · 2026-07-20T16:09:41Z

PR_Github #60404 [ run ] triggered by Bot. Commit: 0089eeb Link to invocation

tensorrt-cicd · 2026-07-20T18:35:36Z

PR_Github #60404 [ run ] completed with state FAILURE. Commit: 0089eeb
/LLM/main/L0_MergeRequest_PR pipeline #48742 (Partly Tested) 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

Shixiaowei02 · 2026-07-21T02:22:32Z

/bot run --disable-fail-fast --stage-list "DGX_B300-4_GPUs-PyTorch-1, GB200-4_GPUs-PyTorch-2, GB200-4_GPUs-PyTorch-3, GB200-4_GPUs-PyTorch-5, GB200-4_GPUs-PyTorch-PerfSanity-1, GB200-4_GPUs-PyTorch-PerfSanity-2, GB200-8_GPUs-2_Nodes-PyTorch-1"

tensorrt-cicd · 2026-07-21T02:29:36Z

PR_Github #60536 [ run ] triggered by Bot. Commit: 0089eeb Link to invocation

tensorrt-cicd · 2026-07-21T04:05:40Z

PR_Github #60536 [ run ] completed with state SUCCESS. Commit: 0089eeb
/LLM/main/L0_MergeRequest_PR pipeline #48855 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

Shixiaowei02 · 2026-07-21T07:25:14Z

/bot skip --comment "Related tests have passed."

tensorrt-cicd · 2026-07-21T07:30:50Z

PR_Github #60631 [ skip ] triggered by Bot. Commit: 0089eeb Link to invocation

tensorrt-cicd · 2026-07-21T07:37:07Z

PR_Github #60631 [ skip ] completed with state SUCCESS. Commit: 0089eeb
Skipping testing for commit 0089eeb

Link to invocation

github-actions Bot assigned Shixiaowei02 Jul 16, 2026

Shixiaowei02 changed the title ~~[None][test] Switch Kimi dis-agg tests to the transceiver v2~~ [None][test] Migrate Kimi dis-agg tests to Transceiver v2 and trim tests Jul 16, 2026

Shixiaowei02 changed the title ~~[None][test] Migrate Kimi dis-agg tests to Transceiver v2 and trim tests~~ [TRTLLM-13639][test] Migrate Kimi dis-agg tests to Transceiver v2 and trim tests Jul 16, 2026

Shixiaowei02 force-pushed the dev/xiaoweis/kimi-disagg-py-transceiver branch from 8d16a99 to 853df7a Compare July 16, 2026 07:22

Shixiaowei02 marked this pull request as ready for review July 16, 2026 07:23

Shixiaowei02 requested review from a team as code owners July 16, 2026 07:23

Shixiaowei02 requested review from dc3671, fredricz-20070104, longlee0622, nv-ananjappa, pcastonguay, reasonsolo and yufeiwu-nv July 16, 2026 07:23

coderabbitai Bot reviewed Jul 16, 2026

View reviewed changes

Comment thread tests/integration/defs/accuracy/test_disaggregated_serving.py

Shixiaowei02 force-pushed the dev/xiaoweis/kimi-disagg-py-transceiver branch from 853df7a to ef95e3a Compare July 16, 2026 07:31

yufeiwu-nv approved these changes Jul 16, 2026

View reviewed changes

Shixiaowei02 force-pushed the dev/xiaoweis/kimi-disagg-py-transceiver branch from ef95e3a to d1be051 Compare July 16, 2026 07:56

Shixiaowei02 requested a review from a team as a code owner July 16, 2026 07:56

Shixiaowei02 requested a review from nv-guomingz July 16, 2026 07:56

Shixiaowei02 force-pushed the dev/xiaoweis/kimi-disagg-py-transceiver branch from da7dcf0 to bc28173 Compare July 20, 2026 02:28

Shixiaowei02 force-pushed the dev/xiaoweis/kimi-disagg-py-transceiver branch from bc28173 to 0089eeb Compare July 20, 2026 02:58

coderabbitai Bot mentioned this pull request Jul 20, 2026

[None][chore] Remove all 1k1k cases from QA's disagg side #16586

Merged

Shixiaowei02 enabled auto-merge (squash) July 21, 2026 07:25

litaotju approved these changes Jul 21, 2026

View reviewed changes

dc3671 approved these changes Jul 21, 2026

View reviewed changes

Shixiaowei02 merged commit 9390924 into NVIDIA:main Jul 21, 2026
8 checks passed

Shixiaowei02 deleted the dev/xiaoweis/kimi-disagg-py-transceiver branch July 21, 2026 08:09

coderabbitai Bot mentioned this pull request Jul 21, 2026

[TRTLLM-13948][test] Migrate DeepSeek R1/V3.2 disagg perf cases to transceiver V2 #16669

Merged

1 task

Shixiaowei02 mentioned this pull request Jul 23, 2026

[None][feat] Prefer V2 transceiver backend for Gemma and Llama #16787

Open

1 task

coderabbitai Bot mentioned this pull request Jul 27, 2026

[https://nvbugs/6503299][fix] Default fabric memory KV pool for Python cache transceiver #16832

Open

3 tasks

Uh oh!

Conversation

Shixiaowei02 commented Jul 16, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Test Coverage

PR Checklist

GitHub Bot Help

Summary by CodeRabbit

Uh oh!

Shixiaowei02 commented Jul 16, 2026

Uh oh!

coderabbitai Bot commented Jul 16, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Uh oh!

coderabbitai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

tensorrt-cicd commented Jul 16, 2026

Uh oh!

Shixiaowei02 commented Jul 16, 2026

Uh oh!

Shixiaowei02 commented Jul 16, 2026

Uh oh!

tensorrt-cicd commented Jul 16, 2026

Uh oh!

tensorrt-cicd commented Jul 16, 2026

Uh oh!

tensorrt-cicd commented Jul 16, 2026

Uh oh!

Shixiaowei02 commented Jul 20, 2026

Uh oh!

tensorrt-cicd commented Jul 20, 2026

Uh oh!

Shixiaowei02 commented Jul 20, 2026

Uh oh!

tensorrt-cicd commented Jul 20, 2026

Uh oh!

tensorrt-cicd commented Jul 20, 2026

Uh oh!

tensorrt-cicd commented Jul 20, 2026

Uh oh!

Shixiaowei02 commented Jul 20, 2026

Uh oh!

tensorrt-cicd commented Jul 20, 2026

Uh oh!

tensorrt-cicd commented Jul 20, 2026

Uh oh!

Shixiaowei02 commented Jul 20, 2026

Uh oh!

tensorrt-cicd commented Jul 20, 2026

Uh oh!

tensorrt-cicd commented Jul 20, 2026

Uh oh!

Shixiaowei02 commented Jul 21, 2026

Uh oh!

tensorrt-cicd commented Jul 21, 2026

Uh oh!

tensorrt-cicd commented Jul 21, 2026

Uh oh!

Shixiaowei02 commented Jul 21, 2026

Uh oh!

tensorrt-cicd commented Jul 21, 2026

Uh oh!

tensorrt-cicd commented Jul 21, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

7 participants

Shixiaowei02 commented Jul 16, 2026 •

edited

Loading

coderabbitai Bot commented Jul 16, 2026 •

edited

Loading