[None][doc] Cherry-pick deployment guide update from 1.1.0rc2 branch to main branch #7774
Conversation
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
📝 WalkthroughWalkthroughDocumentation update to the TRTLLM quick-start guide: increased stream_interval values in TRTLLM and CUTLASS config examples, and added attention_dp_config with balance and batching parameters in the CUTLASS block. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes ✨ Finishing touches🧪 Generate unit tests
Tip 👮 Agentic pre-merge checks are now available in preview!Pro plan users can now enable pre-merge checks in their settings to enforce checklists before merging PRs.
Please see the documentation for more information. Example: reviews:
pre_merge_checks:
custom_checks:
- name: "Undocumented Breaking Changes"
mode: "warning"
instructions: |
Pass/fail criteria: All breaking changes to public APIs, CLI flags, environment variables, configuration keys, database schemas, or HTTP/GraphQL endpoints must be documented in the "Breaking Change" section of the PR description and in CHANGELOG.md. Exclude purely internal or private changes (e.g., code not exported from package entry points or explicitly marked as internal).Please share your feedback with us on this Discord post. 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 Pre-merge checks❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (6)
docs/source/deployment-guide/quick-start-recipe-for-gpt-oss-on-trtllm.md (6)
68-78: Use a quoted heredoc to avoid accidental shell expansion; keep YAML indentation consistent.
- Quote EOF to prevent variable expansion in copied configs.
- Use consistent 2‑space indent under moe_config (matches cuda_graph_config block).
Apply this diff:
-EXTRA_LLM_API_FILE=/tmp/config.yml - -cat << EOF > ${EXTRA_LLM_API_FILE} +EXTRA_LLM_API_FILE=/tmp/config.yml + +cat <<'EOF' > "${EXTRA_LLM_API_FILE}" enable_attention_dp: false cuda_graph_config: enable_padding: true max_batch_size: 720 moe_config: - backend: TRTLLM + backend: TRTLLM stream_interval: 20 num_postprocess_workers: 4 EOF
75-75: Document the rationale/trade‑off for stream_interval: 20.Increasing stream_interval reduces host I/O but can increase perceived latency for streamed tokens. Add a brief note on when to raise/lower it (e.g., throughput vs. TTFT/ITL targets).
85-99: Mirror heredoc quoting and indentation; minor YAML hygiene.Same quoting/indent consistency as the TRTLLM block; keeps examples copy‑safe and uniform.
Apply this diff:
-EXTRA_LLM_API_FILE=/tmp/config.yml - -cat << EOF > ${EXTRA_LLM_API_FILE} +EXTRA_LLM_API_FILE=/tmp/config.yml + +cat <<'EOF' > "${EXTRA_LLM_API_FILE}" enable_attention_dp: true cuda_graph_config: enable_padding: true max_batch_size: 720 moe_config: - backend: CUTLASS + backend: CUTLASS stream_interval: 20 num_postprocess_workers: 4 attention_dp_config: - enable_balance: true - batching_wait_iters: 50 - timeout_iters: 1 + enable_balance: true + batching_wait_iters: 50 + timeout_iters: 1 EOF
222-223: Fix typo and remove lingering TODO before merge.“Compeletions” → “Completions”; replace the placeholder text or drop the entire TODO.
Apply this diff:
-TODO: Use Chat Compeletions API / Responses API as the example after the PR is merged. +Note: Example below will be updated to use the Chat Completions / Responses API after the related PR merges. (If already merged, replace this line with the final example.)
25-31: Minor wording polish: “support matrix” → “support matrices”; clarify default.Consider: “There are multiple MoE backends in TRT‑LLM. The table below summarizes supported configurations. The default backend is CUTLASS.”
55-57: Add stability note about rc vs non‑rc images.Since rc images are weekly and may change behavior, add a one‑liner reminding users to pin exact tags for reproducibility.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
docs/source/deployment-guide/quick-start-recipe-for-gpt-oss-on-trtllm.md(2 hunks)
⏰ 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 (3)
docs/source/deployment-guide/quick-start-recipe-for-gpt-oss-on-trtllm.md (3)
46-47: Align container tag with the documented features/branch.Example uses release:1.0.0rc6 while this PR cherry-picks from 1.1.0rc2. Please confirm the example image contains the attention DP options and stream_interval behavior shown below, or update the tag/note the minimum required version.
106-117: Good: server launch command is consistent with the YAML examples.Flags align with the config blocks and Hugging Face model usage. No blockers.
If there’s a known minimum driver/runtime for Blackwell with attention DP enabled, consider adding it near Prerequisites.
92-97: Confirmed: option names match TorchLlmArgs — verify image tagattention_dp_config.{enable_balance, batching_wait_iters, timeout_iters} and stream_interval are defined in tensorrt_llm/llmapi/llm_args.py; runtime/CLI variants (attention_dp_time_out_iters, attention_dp_batching_wait_iters, attention_dp_enable_balance) appear in tensorrt_llm/_torch/pyexecutor/config.py and examples/llm-api/quickstart_advanced.py. Confirm the serve image tag you use contains these definitions.
|
/bot run --disable-fail-fast |
|
PR_Github #18834 [ run ] triggered by Bot |
|
PR_Github #18834 [ run ] completed with state |
|
@nv-guomingz could you help merge? CI passed |
…to main branch (NVIDIA#7774) Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
…to main branch (NVIDIA#7774) Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
…to main branch (NVIDIA#7774) Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
3 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.
Details
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.