KEMBAR78
[TRTLLM-7964][infra] Set nixl to default cache transceiver backend by bo-nv · Pull Request #7926 · NVIDIA/TensorRT-LLM · GitHub
Skip to content

Conversation

@bo-nv
Copy link
Collaborator

@bo-nv bo-nv commented Sep 23, 2025

Summary by CodeRabbit

  • New Features

    • Default cache transceiver backend is now NIXL when “DEFAULT” is selected. Environment-based selection updated accordingly.
  • Documentation

    • Updated backend default in disaggregated serving docs and examples.
    • Installation guides now include libzmq3-dev alongside libopenmpi-dev.
  • Chores

    • Docker UCX/NIXL install scripts no longer persist LD_LIBRARY_PATH to ENV files, reducing environment side effects.

Description

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)

  • Any new dependencies have been scanned for license and vulnerabilities

  • CODEOWNERS updated if ownership changes

  • Documentation updated as needed

  • 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

/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...

Provide a user friendly way for developers to interact with a Jenkins server.

Run /bot [-h|--help] to print this help message.

See details below for each supported subcommand.

run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]

Launch build/test pipelines. All previously running jobs will be killed.

--reuse-test (optional)pipeline-id (OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.

--disable-reuse-test (OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.

--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.

--stage-list "A10-PyTorch-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.

--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.

--test-backend "pytorch, cpp" (OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.

--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.

--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".

--detailed-log (OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.

--debug (OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in the stage-list parameter to access the appropriate container environment. Note: Does NOT update GitHub check status.

For guidance on mapping tests to stage names, see docs/source/reference/ci-overview.md
and the scripts/test_to_stage_mapping.py helper.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

@bo-nv bo-nv requested review from a team as code owners September 23, 2025 09:22
@bo-nv bo-nv marked this pull request as draft September 23, 2025 09:22
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Sep 23, 2025

📝 Walkthrough

Walkthrough

The default CacheTransceiver backend for DEFAULT was switched from UCX to NIXL in C++ and Python. Env-based selection logic in the Python executor was adjusted. Multiple docs were updated to reflect the new default and to add libzmq3-dev to install commands. Docker install scripts stopped appending LD_LIBRARY_PATH to the ENV file.

Changes

Cohort / File(s) Summary
Backend default change (code)
cpp/tensorrt_llm/batch_manager/cacheTransceiver.cpp, tensorrt_llm/_torch/pyexecutor/kv_cache_transceiver.py
Change DEFAULT backend from UCX to NIXL; adjust Python env-based selection logic accordingly.
Docs: backend default update
docs/source/features/disagg-serving.md, examples/disaggregated/README.md
Update documented default backend from UCX to NIXL for cache_transceiver_config.
Docs: install prerequisites update
docs/source/features/auto_deploy/auto-deploy.md, docs/source/installation/linux.md, docs/source/torch/auto_deploy/auto-deploy.md, examples/auto_deploy/README.md
Add libzmq3-dev to apt-get install lines alongside libopenmpi-dev.
Docker install scripts: ENV export removal
docker/common/install_nixl.sh, docker/common/install_ucx.sh
Remove appending of LD_LIBRARY_PATH export to the ENV file after installation; rest of flow unchanged.

Sequence Diagram(s)

sequenceDiagram
  autonumber
  participant App as App
  participant Cfg as Config
  participant Env as Environment
  participant Sel as BackendSelector
  participant CT as CacheTransceiver

  App->>Cfg: Read backend setting
  App->>Env: Read env vars (e.g., *_KVCACHE)
  App->>Sel: Request backend decision (Cfg, Env)

  rect rgba(200,220,255,0.25)
    Sel->>Sel: If Cfg.backend is explicit (UCX/NIXL/MPI)
    Sel-->>App: Return explicit backend
  end

  alt Cfg.backend == DEFAULT
    Sel->>Sel: Check env-based triggers (e.g., MPI/others)
    Sel->>Sel: If no env override, choose NIXL (new default)
    Sel-->>App: Return chosen backend
  end

  App->>CT: Initialize with selected backend
  CT-->>App: Ready
  note over App,CT: DEFAULT now resolves to NIXL when no env override
Loading

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

Pre-merge checks and finishing touches

❌ Failed checks (2 warnings)
Check name Status Explanation Resolution
Docstring Coverage ⚠️ Warning Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%. You can run @coderabbitai generate docstrings to improve docstring coverage.
Description Check ⚠️ Warning The pull request description consists solely of the template instructions and has no filled-in title line, no description of the change and reasoning, and no test coverage details. Without these required sections, the PR does not meet the repository’s description template requirements. Please replace the placeholder template with your actual PR title in the required format, provide a concise summary of the issue and solution under the Description heading, and list the relevant test cases under Test Coverage to ensure the template is fully populated.
✅ Passed checks (1 passed)
Check name Status Explanation
Title Check ✅ Passed The pull request title "[TRTLLM-7964][infra] Set nixl to default cache transceiver backend" accurately and directly summarizes the primary change across the pull request. The changeset demonstrates a consistent theme of switching the default cache transceiver backend from UCX to NIXL, which is reflected in code changes (cpp/tensorrt_llm/batch_manager/cacheTransceiver.cpp and tensorrt_llm/_torch/pyexecutor/kv_cache_transceiver.py) and documentation updates (disagg-serving.md, examples/disaggregated/README.md). While secondary changes exist (removing LD_LIBRARY_PATH exports and adding libzmq3-dev dependencies), the title captures the core objective and main point of the changeset effectively. The title is clear, concise, and specific enough that a reviewer can immediately understand the primary intention.
✨ Finishing touches
  • 📝 Generate docstrings
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 0

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)
tensorrt_llm/_torch/pyexecutor/kv_cache_transceiver.py (1)

1-3: Add SPDX header

Per repo guidelines, prepend the NVIDIA Apache-2.0 SPDX header.

Apply this diff at file top:

+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
🧹 Nitpick comments (3)
docs/source/features/disagg-serving.md (1)

109-109: Default is NIXL — consider updating examples for consistency

Since DEFAULT now maps to NIXL, consider using backend: DEFAULT or backend: NIXL in the example YAMLs (Lines 119 and 126 currently show UCX) to avoid confusion.

tensorrt_llm/_torch/pyexecutor/kv_cache_transceiver.py (1)

41-46: Support NIXL env trigger for parity with C++

Add TRTLLM_USE_NIXL_KVCACHE so Python matches C++ env selection and explicit NIXL overrides are honored.

Apply this diff:

-        # Ordered by priority
-        env_vars = [("TRTLLM_USE_UCX_KVCACHE", BackendTypeCpp.UCX),
-                    ("TRTLLM_USE_MPI_KVCACHE", BackendTypeCpp.MPI)]
+        # Ordered by priority: UCX > NIXL > MPI
+        env_vars = [("TRTLLM_USE_UCX_KVCACHE", BackendTypeCpp.UCX),
+                    ("TRTLLM_USE_NIXL_KVCACHE", BackendTypeCpp.NIXL),
+                    ("TRTLLM_USE_MPI_KVCACHE", BackendTypeCpp.MPI)]
examples/disaggregated/README.md (1)

15-15: List MPI as deprecated option for completeness

Docs elsewhere mention MPI (deprecated). Include it here to align.

Apply this diff:

-  # KV cache transmission backend. Valid options include `DEFAULT` (i.e., NIXL), `UCX`, `NIXL`.
+  # KV cache transmission backend. Valid options include `DEFAULT` (NIXL), `UCX`, `NIXL`, and `MPI` (deprecated).
📜 Review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 3ba19b6 and c74e881.

📒 Files selected for processing (10)
  • cpp/tensorrt_llm/batch_manager/cacheTransceiver.cpp (1 hunks)
  • docker/common/install_nixl.sh (0 hunks)
  • docker/common/install_ucx.sh (0 hunks)
  • docs/source/features/auto_deploy/auto-deploy.md (1 hunks)
  • docs/source/features/disagg-serving.md (1 hunks)
  • docs/source/installation/linux.md (1 hunks)
  • docs/source/torch/auto_deploy/auto-deploy.md (1 hunks)
  • examples/auto_deploy/README.md (1 hunks)
  • examples/disaggregated/README.md (1 hunks)
  • tensorrt_llm/_torch/pyexecutor/kv_cache_transceiver.py (1 hunks)
💤 Files with no reviewable changes (2)
  • docker/common/install_ucx.sh
  • docker/common/install_nixl.sh
🧰 Additional context used
📓 Path-based instructions (6)
**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Use only spaces, no tabs; indent with 4 spaces.

Files:

  • tensorrt_llm/_torch/pyexecutor/kv_cache_transceiver.py
  • cpp/tensorrt_llm/batch_manager/cacheTransceiver.cpp
**/*.py

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

**/*.py: Python code must target Python 3.8+.
Indent Python code with 4 spaces; do not use tabs.
Maintain module namespace when importing; prefer 'from package.subpackage import foo' then 'foo.SomeClass()' instead of importing the class directly.
Python filenames should be snake_case (e.g., some_file.py).
Python classes use PascalCase names.
Functions and methods use snake_case names.
Local variables use snake_case; prefix 'k' for variables that start with a number (e.g., k_99th_percentile).
Global variables use upper SNAKE_CASE prefixed with 'G' (e.g., G_MY_GLOBAL).
Constants use upper SNAKE_CASE (e.g., MY_CONSTANT).
Avoid shadowing variables from an outer scope.
Initialize all externally visible members of a class in the constructor.
Prefer docstrings for interfaces that may be used outside a file; comments for in-function or file-local interfaces.
Use Google-style docstrings for classes and functions (Sphinx-parsable).
Document attributes and variables inline so they render under the class/function docstring.
Avoid reflection when a simpler, explicit approach suffices (e.g., avoid dict(**locals()) patterns).
In try/except, catch the most specific exceptions possible.
For duck-typing try/except, keep the try body minimal and use else for the main logic.

Files:

  • tensorrt_llm/_torch/pyexecutor/kv_cache_transceiver.py
**/*.{cpp,cxx,cc,h,hpp,hh,hxx,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Prepend the NVIDIA Apache-2.0 copyright header with current year to the top of all source files (e.g., .cpp, .h, .cu, .py).

Files:

  • tensorrt_llm/_torch/pyexecutor/kv_cache_transceiver.py
  • cpp/tensorrt_llm/batch_manager/cacheTransceiver.cpp
**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh}: Namespace closing braces must include a trailing comment with the namespace name (e.g., '} // namespace foo').
Prefer const or constexpr variables over #define for constants.
Declare variables that are not modified after initialization as const.
Avoid magic literals in code; except for 0, nullptr, true, false. Use named constants for comparisons and logic.
Use Allman brace style for formatting.
Place the semicolon of an empty for/while loop on a new line.
Bodies of switch/while/do-while/for must be compound statements (brace-delimited), and if/else must always be followed by brace-delimited statements.
Type names (e.g., classes) must be CamelCase starting with an uppercase letter (e.g., FooBar).
Local variables, methods, and namespaces use lowerCamelCase (e.g., localFooBar).
Non-magic-number global variables that are non-static and not in an anonymous namespace must be lowerCamelCase prefixed with 'g' (e.g., gDontUseGlobalFoos).
Non-magic-number globals that are static or in an anonymous namespace use lowerCamelCase prefixed with 's' (e.g., sMutableStaticGlobal).
Locally visible static variables use lowerCamelCase with 's' prefix (e.g., static std::once_flag sFlag).
Private/protected member variables use 'm' prefix with CamelCase (e.g., mNbFooValues). Public members may omit, but 'm' is encouraged for clarity.
Constants (enums, global constants, static constants, and function-scope magic/literal constants) use uppercase SNAKE_CASE with 'k' prefix (e.g., kDIGIT_NUM).
Function-scope constants that are not magic numbers or literals are named like non-constant variables (e.g., bool const pass = a && b).
If macros are necessary, name them in UPPER_SNAKE_CASE (e.g., FOO_VERSION) and prefer constants over #define.
Use LLVM clang-format; wrap lines at a maximum of 120 columns; use '// clang-format off/on' sparingly with justification.
Use smart pointers for heap allocations; prefer unique_ptr for sole ownership, shared_ptr for shared...

Files:

  • cpp/tensorrt_llm/batch_manager/cacheTransceiver.cpp
**/*.{cpp,cxx,cc,cu,h,hpp,hh,hxx,cuh}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

C++ filenames should be lowerCamelCase (first letter lowercase) and must be case-insensitive unique within a compilation target.

Files:

  • cpp/tensorrt_llm/batch_manager/cacheTransceiver.cpp
**/*.{h,hpp,hh,hxx,cpp,cxx,cc}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

**/*.{h,hpp,hh,hxx,cpp,cxx,cc}: Prefer anonymous namespaces over 'static' for internal linkage of functions.
All templates (class/function/member/static) must be instantiated at least once; non-POD classes should have private data members.

Files:

  • cpp/tensorrt_llm/batch_manager/cacheTransceiver.cpp
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
  • GitHub Check: Pre-commit Check
🔇 Additional comments (5)
docs/source/installation/linux.md (1)

19-19: Add libzmq3-dev prerequisite — LGTM

Change aligns install docs with new NIXL default.

docs/source/features/auto_deploy/auto-deploy.md (1)

31-31: Install libzmq3-dev — LGTM

Matches NIXL dependency requirements.

examples/auto_deploy/README.md (1)

12-12: Install libzmq3-dev — LGTM

Consistent with installation docs and NIXL default.

docs/source/torch/auto_deploy/auto-deploy.md (1)

31-31: Install libzmq3-dev — LGTM

In sync with other docs.

cpp/tensorrt_llm/batch_manager/cacheTransceiver.cpp (1)

92-93: DEFAULT→NIXL fallback — LGTM

Matches Python and docs; env-based overrides remain intact.

@bo-nv bo-nv force-pushed the user/bo/rel-1.2-nixl-default branch from c74e881 to 6cc619a Compare September 25, 2025 12:19
@bo-nv
Copy link
Collaborator Author

bo-nv commented Sep 25, 2025

/bot run --stage-list "Build-Docker-Images"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19949 [ run ] triggered by Bot

@bo-nv
Copy link
Collaborator Author

bo-nv commented Sep 25, 2025

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

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19970 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19949 [ run ] completed with state ABORTED
LLM/main/L0_MergeRequest_PR #15019 (Blue Ocean) completed with status: ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #19970 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15033 completed with status: 'FAILURE'

@bo-nv
Copy link
Collaborator Author

bo-nv commented Sep 26, 2025

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

@tensorrt-cicd
Copy link
Collaborator

PR_Github #20072 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #20072 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15122 completed with status: 'SUCCESS'

@bo-nv bo-nv marked this pull request as ready for review September 28, 2025 14:01
@bo-nv bo-nv requested a review from a team as a code owner September 28, 2025 14:01
@bo-nv bo-nv requested a review from tburt-nv September 28, 2025 14:01
Copy link
Collaborator Author

@bo-nv bo-nv left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Merge after updating docker images (jenkins/current_image_tags.properties)

@pcastonguay
Copy link
Collaborator

@bo-nv anything blocking this MR?

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21758 [ run ] triggered by Bot. Commit: 50f55ab

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21758 [ run ] completed with state SUCCESS. Commit: 50f55ab
/LLM/main/L0_MergeRequest_PR pipeline #16397 completed with status: 'FAILURE'

@bo-nv
Copy link
Collaborator Author

bo-nv commented Oct 18, 2025

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

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21766 [ run ] triggered by Bot. Commit: 50f55ab

Signed-off-by: Bo Deng <deemod@nvidia.com>
@bo-nv
Copy link
Collaborator Author

bo-nv commented Oct 18, 2025

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

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21767 [ run ] triggered by Bot. Commit: 809292c

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21766 [ run ] completed with state ABORTED. Commit: 50f55ab
LLM/main/L0_MergeRequest_PR #16405 (Blue Ocean) completed with status: ABORTED

Signed-off-by: Bo Deng <deemod@nvidia.com>
@bo-nv
Copy link
Collaborator Author

bo-nv commented Oct 18, 2025

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

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21769 [ run ] triggered by Bot. Commit: dc72927

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21767 [ run ] completed with state ABORTED. Commit: 809292c
LLM/main/L0_MergeRequest_PR #16406 (Blue Ocean) completed with status: ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21769 [ run ] completed with state SUCCESS. Commit: dc72927
/LLM/main/L0_MergeRequest_PR pipeline #16408 completed with status: 'FAILURE'

@bo-nv
Copy link
Collaborator Author

bo-nv commented Oct 18, 2025

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

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21777 [ run ] triggered by Bot. Commit: dc72927

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21777 [ run ] completed with state SUCCESS. Commit: dc72927
/LLM/main/L0_MergeRequest_PR pipeline #16415 completed with status: 'FAILURE'

@bo-nv
Copy link
Collaborator Author

bo-nv commented Oct 19, 2025

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

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21785 [ run ] triggered by Bot. Commit: dc72927

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21785 [ run ] completed with state SUCCESS. Commit: dc72927
/LLM/main/L0_MergeRequest_PR pipeline #16423 completed with status: 'FAILURE'

@bo-nv
Copy link
Collaborator Author

bo-nv commented Oct 19, 2025

PR_Github #21785 [ run ] completed with state SUCCESS. Commit: dc72927 /LLM/main/L0_MergeRequest_PR pipeline #16423 completed with status: 'FAILURE'

The root cause of the failed test is tensorrt_llm/lib is missing in LD_LIBRARY_PATH, not related to this PR, will file a bug later.

https://prod.blsm.nvidia.com/sw-tensorrt-top-1/blue/organizations/jenkins/LLM%2Fmain%2FL0_Test-x86_64-Multi-GPU/detail/L0_Test-x86_64-Multi-GPU/1755/pipeline/745/

@bo-nv
Copy link
Collaborator Author

bo-nv commented Oct 19, 2025

/mbot run

@bo-nv
Copy link
Collaborator Author

bo-nv commented Oct 19, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21796 [ run ] triggered by Bot. Commit: dc72927

@bo-nv
Copy link
Collaborator Author

bo-nv commented Oct 19, 2025

/bot skip --comment "https://prod.blsm.nvidia.com/sw-tensorrt-top-1/job/LLM/job/main/job/L0_MergeRequest_PR/16423/, the failed case is a known issue and not related to the PR."

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21798 [ skip ] triggered by Bot. Commit: dc72927

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21796 [ run ] completed with state ABORTED. Commit: dc72927
LLM/main/L0_MergeRequest_PR #16430 (Blue Ocean) completed with status: ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21798 [ skip ] completed with state SUCCESS. Commit: dc72927
Skipping testing for commit dc72927

@bo-nv bo-nv merged commit dd25595 into NVIDIA:main Oct 19, 2025
5 checks passed
govind-ramnarayan pushed a commit to nv-auto-deploy/TensorRT-LLM that referenced this pull request Oct 21, 2025
yufeiwu-nv pushed a commit to yufeiwu-nv/TensorRT-LLM that referenced this pull request Oct 24, 2025
…VIDIA#7926)

Signed-off-by: Bo Deng <deemod@nvidia.com>
Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.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.

8 participants