[None][doc] update ucx env description in doc #8747
Conversation
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
|
/bot skip --comment "only doc update" |
📝 WalkthroughWalkthroughUpdates documentation for disaggregated serving by reformatting the UCX_MAX_RNDV_RAILS environment variable entry with clarification text and adding a new UCX_MAX_RMA_RAILS environment variable entry with guidance for NIXL backend usage. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~5 minutes
Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✨ Finishing touches🧪 Generate unit tests (beta)
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. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
docs/source/features/disagg-serving.md(1 hunks)
🧰 Additional context used
🪛 LanguageTool
docs/source/features/disagg-serving.md
[grammar] ~216-~216: Ensure spelling is correct
Context: ...A_RAILS=1 to reduce contention for NIXL communicaiton backend. ## Troubleshooting and FAQ #...
(QB_NEW_EN_ORTHOGRAPHY_ERROR_IDS_1)
⏰ 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
| * `UCX_MAX_RNDV_RAILS` : With the default value 2, UCX attempts to use two InfiniBand (IB) NIC devices per GPU for Rendezvous (RNDV) transfers. When both the context and generation instances enable tensor- and expert-parallel (TEP), multiple TP ranks may transfer KV cache concurrently. Because each TP rank can use up to two NIC devices, some NIC devices can be shared across GPUs, causing contention and reduced throughput. Setting UCX_MAX_RNDV_RAILS=1 can reduce contention in this case for UCX communication backend. | ||
|
|
||
| * `UCX_MAX_RMA_RAILS` : It is recommended to set UCX_MAX_RMA_RAILS=1 to reduce contention for NIXL communicaiton backend. |
There was a problem hiding this comment.
Fix spelling error and verify consistency.
Line 216 contains a spelling error: communicaiton should be communication. Additionally, ensure consistency in the phrasing style between the UCX_MAX_RNDV_RAILS and UCX_MAX_RMA_RAILS entries—the first entry uses more detailed explanation, while the second is more concise. This difference may be intentional for brevity, but review for consistency.
Apply this diff to fix the spelling error:
-* `UCX_MAX_RMA_RAILS` : It is recommended to set UCX_MAX_RMA_RAILS=1 to reduce contention for NIXL communicaiton backend.
+* `UCX_MAX_RMA_RAILS` : It is recommended to set UCX_MAX_RMA_RAILS=1 to reduce contention for NIXL communication backend.📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| * `UCX_MAX_RNDV_RAILS` : With the default value 2, UCX attempts to use two InfiniBand (IB) NIC devices per GPU for Rendezvous (RNDV) transfers. When both the context and generation instances enable tensor- and expert-parallel (TEP), multiple TP ranks may transfer KV cache concurrently. Because each TP rank can use up to two NIC devices, some NIC devices can be shared across GPUs, causing contention and reduced throughput. Setting UCX_MAX_RNDV_RAILS=1 can reduce contention in this case for UCX communication backend. | |
| * `UCX_MAX_RMA_RAILS` : It is recommended to set UCX_MAX_RMA_RAILS=1 to reduce contention for NIXL communicaiton backend. | |
| * `UCX_MAX_RNDV_RAILS` : With the default value 2, UCX attempts to use two InfiniBand (IB) NIC devices per GPU for Rendezvous (RNDV) transfers. When both the context and generation instances enable tensor- and expert-parallel (TEP), multiple TP ranks may transfer KV cache concurrently. Because each TP rank can use up to two NIC devices, some NIC devices can be shared across GPUs, causing contention and reduced throughput. Setting UCX_MAX_RNDV_RAILS=1 can reduce contention in this case for UCX communication backend. | |
| * `UCX_MAX_RMA_RAILS` : It is recommended to set UCX_MAX_RMA_RAILS=1 to reduce contention for NIXL communication backend. |
🧰 Tools
🪛 LanguageTool
[grammar] ~216-~216: Ensure spelling is correct
Context: ...A_RAILS=1 to reduce contention for NIXL communicaiton backend. ## Troubleshooting and FAQ #...
(QB_NEW_EN_ORTHOGRAPHY_ERROR_IDS_1)
🤖 Prompt for AI Agents
In docs/source/features/disagg-serving.md around lines 214 to 216, fix the
spelling mistake "communicaiton" to "communication" in the UCX_MAX_RMA_RAILS
entry and make the phrasing consistent with the UCX_MAX_RNDV_RAILS entry by
expanding the RMA entry to match the level of detail (mention that setting
UCX_MAX_RMA_RAILS=1 reduces NIC contention for the UCX communication backend
when multiple TP ranks may transfer KV cache concurrently, or otherwise reword
both entries to follow the same concise style).
|
PR_Github #22835 [ skip ] triggered by Bot. Commit: |
|
PR_Github #22835 [ skip ] completed with state |
2 participants
Summary by CodeRabbit
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 thestage-listparameter 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.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip 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-pipelineReuse 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.