[TRTLLM-8431][doc] update public doc and example, add etcd auto-scaling tests #8602
Conversation
reasonsolo
requested review from
Shixiaowei02,
Tabrizian,
chuangz0 and
nv-guomingz
📝 WalkthroughWalkthroughThe changes expand disaggregated service documentation with complete service discovery guidance, introduce a Slurm launch script demonstrating dynamic scaling with optional etcd integration, and refine URI scheme validation in cluster storage to require explicit protocol schemes. Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant Slurm as Slurm Job
participant Etcd as Optional ETCD<br/>Service
participant Disagg as Disaggregated<br/>Proxy
participant Ctx as Context<br/>Service
participant Gen as Generation<br/>Service
User->>Slurm: Submit launch.slurm job
Slurm->>Slurm: Determine first node as server
alt enable_etcd == "1"
Slurm->>Etcd: Launch etcd container on disagg node
Etcd-->>Slurm: etcd:// cluster_uri ready
else
Slurm->>Slurm: Set http:// cluster_uri on disagg node
end
Slurm->>Disagg: Generate disagg_config.yaml<br/>Launch proxy service
Disagg-->>Slurm: Proxy ready (port 8000)
Slurm->>Ctx: Generate ctx_extra-llm-api-config.yaml<br/>Launch context service (2×4-GPU nodes)
Ctx-->>Slurm: Context service ready (port 8001)
Slurm->>Gen: Generate gen_extra-llm-api-config.yaml<br/>Launch generation service (1×4-GPU node)
Gen-->>Slurm: Generation service ready (port 8002)
Disagg->>Ctx: Cluster discovery & heartbeat
Disagg->>Gen: Cluster discovery & heartbeat
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 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: 7
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
examples/disaggregated/README.md(2 hunks)examples/disaggregated/slurm/service_discovery_example/launch.slurm(1 hunks)tensorrt_llm/serve/cluster_storage.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (3)
**/*.{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/serve/cluster_storage.py
**/*.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/serve/cluster_storage.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/serve/cluster_storage.py
🪛 LanguageTool
examples/disaggregated/README.md
[grammar] ~230-~230: Ensure spelling is correct
Context: ...g_cluster` configuration values, or the disaggrated server may not be able to keep alive or...
(QB_NEW_EN_ORTHOGRAPHY_ERROR_IDS_1)
[grammar] ~236-~236: Ensure spelling is correct
Context: ...ith the same disagg_cluster, then the disaggragated server can discover the new servers and...
(QB_NEW_EN_ORTHOGRAPHY_ERROR_IDS_1)
🪛 markdownlint-cli2 (0.18.1)
examples/disaggregated/README.md
213-213: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🪛 Ruff (0.14.1)
tensorrt_llm/serve/cluster_storage.py
111-111: Avoid specifying long messages outside the exception class
(TRY003)
⏰ 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 (4)
tensorrt_llm/serve/cluster_storage.py (2)
106-111: Explicit URI scheme validation improves correctness.The change to require explicit
http://,https://, oretcd://prefixes prevents ambiguous URIs and aligns with the usage patterns in the documentation and example scripts.
114-119: LGTM!The client factory now mirrors the server factory's explicit scheme validation, ensuring consistency across both creation paths.
examples/disaggregated/slurm/service_discovery_example/launch.slurm (2)
31-38: Verify hostname configuration for external access.Line 32 sets
hostname: localhost, which will prevent external clients from accessing the disaggregated server. If the service should be accessible from other nodes or external clients, consider using0.0.0.0or the actual hostname.If external access is intended, apply this change:
cat >${work_path}/disagg_config.yaml << EOL -hostname: localhost +hostname: 0.0.0.0 port: ${disagg_port}
60-65: LGTM!The context service configuration correctly matches
tp_size=8with the Slurm task allocation (-N 2 --ntasks-per-node=4= 8 total tasks).
examples/disaggregated/slurm/service_discovery_example/launch.slurm
Outdated
Show resolved
Hide resolved
examples/disaggregated/slurm/service_discovery_example/launch.slurm
Outdated
Show resolved
Hide resolved
examples/disaggregated/slurm/service_discovery_example/launch.slurm
Outdated
Show resolved
Hide resolved
reasonsolo
force-pushed
the
tllm8431_sddoc
branch
2 times, most recently
from
54095ce to
8248731
Compare
reasonsolo
requested review from
a team
and removed request for
a team,
Tabrizian,
chuangz0,
nv-guomingz and
zeroepoch
|
/bot run |
|
PR_Github #22359 [ run ] triggered by Bot. Commit: |
|
PR_Github #22359 [ run ] completed with state |
|
/bot run --disable-fail-fast |
|
PR_Github #22384 [ run ] triggered by Bot. Commit: |
|
PR_Github #22384 [ run ] completed with state |
|
/bot run --disable-fail-fast |
|
PR_Github #22437 [ run ] triggered by Bot. Commit: |
|
PR_Github #22437 [ run ] completed with state |
|
/bot run --disable-fail-fast |
|
PR_Github #22567 [ run ] triggered by Bot. Commit: |
|
PR_Github #22567 [ run ] completed with state |
reasonsolo
changed the title
Signed-off-by: Lizhi Zhou <[email protected]>
Signed-off-by: Lizhi Zhou <[email protected]>
Signed-off-by: Lizhi Zhou <[email protected]>
Signed-off-by: Lizhi Zhou <[email protected]>
Signed-off-by: Lizhi Zhou <[email protected]>
reasonsolo
force-pushed
the
tllm8431_sddoc
branch
from
dd639bd to
b574f45
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #22629 [ run ] triggered by Bot. Commit: |
|
PR_Github #22629 [ run ] completed with state |
|
/bot run --disable-fail-fast |
|
PR_Github #22658 [ run ] triggered by Bot. Commit: |
|
PR_Github #22658 [ run ] completed with state |
5 participants
Summary by CodeRabbit
Documentation
Bug Fixes
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.