[None][fix] Updated blog9_Deploying_GPT_OSS_on_TRTLLM #7260
Conversation
Signed-off-by: Maurits de Groot <[email protected]>
📝 WalkthroughWalkthroughDocumentation updates to the TensorRT-LLM deployment blog: updated Docker image tag to 1.1.0rc1, clarified local model path usage outside code blocks, removed redundant notes/commands, and cleaned code blocks. No code or API changes. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Possibly related PRs
Suggested labels
Suggested reviewers
Tip 🔌 Remote MCP (Model Context Protocol) integration is now available!Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats. ✨ Finishing Touches🧪 Generate unit tests
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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
![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
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
docs/source/blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.md (2)
222-222: Copy-paste breakage: backslash before trailing inline commentIn bash, a line-continuation backslash must be the last non-whitespace character on the line. The current lines have a backslash followed by spaces and a comment, which breaks the command when pasted.
Fix both instances:
- --max_batch_size ${max_batch_size} \ # E.g., 1 + # E.g., 1 + --max_batch_size ${max_batch_size} \- --max_batch_size ${max_batch_size} \ # E.g., 640 + # E.g., 640 + --max_batch_size ${max_batch_size} \Alternatively, drop the continuation on these lines and keep the inline comment, but ensure the overall command still parses.
Also applies to: 240-240
105-110: Typo in bullet listThis line starts with “s- ” instead of “- ”, causing a malformed list item in the rendered markdown.
-s- `cuda_graph_config.max_batch_size` is the maximum batch size for CUDA graph. +- `cuda_graph_config.max_batch_size` is the maximum batch size for CUDA graph.
🧹 Nitpick comments (4)
docs/source/blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.md (4)
209-211: Tighten phrasing and placement of the noteMinor grammar/readability: move the note to its own paragraph above the “run” sentence and simplify tone.
Apply:
-We can use `trtllm-serve` to serve the model by translating the benchmark commands above. For low-latency configuration, run: -**Note:** You can also point to a local path containing the model weights instead of the HF repo (e.g., `${local_model_path}`). +Use `trtllm-serve` to translate the benchmark settings into a serving command. + +Note: You can point to a local path containing the model weights instead of the HF repo (for example, `${local_model_path}`). + +For the low-latency configuration, run:If you prefer, I can sweep the doc for similar tone/grammar nits in one pass.
118-135: Parameter name differs between bench and serve; add a small note to avoid user confusionThe benchmarking command uses
--kv_cache_free_gpu_mem_fractionwhiletrtllm-serveuses--kv_cache_free_gpu_memory_fraction. Both are correct for their respective tools, but the subtle difference is easy to miss when toggling between sections. Consider adding a one-line note.Suggested addition (right after the first occurrence in each section):
+Note: The benchmarking tool (`trtllm-bench`) uses `--kv_cache_free_gpu_mem_fraction`, whereas `trtllm-serve` uses `--kv_cache_free_gpu_memory_fraction`.Citations: trtllm-serve option name, and runtime flag docs. (nvidia.github.io)
Also applies to: 213-224, 231-242
261-268: Minor punctuation in example request“NVIDIAs” should be “NVIDIA’s” in the example JSON. Low priority, but it’s user-facing.
- "content": "What is NVIDIAs advantage for inference?" + "content": "What is NVIDIA's advantage for inference?"
28-38: Optional: mirror the “use latest tag” guidance inlineYou already state “change the image tag to match latest release” above the code block. If you want to reduce future churn, consider templating the tag in the snippet itself (e.g., “x.y.z” placeholder) and adding a second example with the concrete 1.1.0rc1 tag. This pattern is used elsewhere in TRT‑LLM docs and nudges readers to check NGC first.
For example:
docker run --rm --ipc=host -it \ ... - nvcr.io/nvidia/tensorrt-llm/release:1.1.0rc1 \ + nvcr.io/nvidia/tensorrt-llm/release:x.y.z \ /bin/bashThen provide a second, copy-ready snippet pinning to 1.1.0rc1.
If you prefer to keep a single snippet, we can insert a short sentence linking to the NGC “Tags” tab that shows 1.1.0rc1 as of Aug 22, 2025. (catalog.ngc.nvidia.com)
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
docs/source/blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.md(2 hunks)
🧰 Additional context used
🧠 Learnings (2)
📓 Common learnings
Learnt from: farshadghodsian
PR: NVIDIA/TensorRT-LLM#7101
File: docs/source/blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.md:36-36
Timestamp: 2025-08-21T00:16:56.457Z
Learning: TensorRT-LLM container release tags in documentation should only reference published NGC container images. The README badge version may be ahead of the actual published container versions.
📚 Learning: 2025-08-21T00:16:56.457Z
Learnt from: farshadghodsian
PR: NVIDIA/TensorRT-LLM#7101
File: docs/source/blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.md:36-36
Timestamp: 2025-08-21T00:16:56.457Z
Learning: TensorRT-LLM container release tags in documentation should only reference published NGC container images. The README badge version may be ahead of the actual published container versions.
Applied to files:
docs/source/blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.md
🪛 LanguageTool
docs/source/blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.md
[grammar] ~209-~209: There might be a mistake here.
Context: ...ove. For low-latency configuration, run: Note: You can also point to a local pa...
(QB_NEW_EN)
⏰ 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 (1)
docs/source/blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.md (1)
36-36: Good change: rc1 tag is now published on NGCThe image tag nvcr.io/nvidia/tensorrt-llm/release:1.1.0rc1 exists and is the latest as of August 22, 2025 on the NGC catalog. This aligns with our guideline to reference only published images.
Citations: NGC page shows “Latest Tag 1.1.0rc1” (modified Aug 22, 2025). (catalog.ngc.nvidia.com)
Maurits-de-Groot
changed the title
Maurits-de-Groot
changed the title
svc-trtllm-gh-bot
added
the
Community want to contribute
Maurits-de-Groot
changed the title
Maurits-de-Groot
changed the title
|
thanks, @Maurits-de-Groot! @DanBlanaru: this is related to the question we discussed on Slack related to the Nebius. |
|
/bot skip --comment "No need to run full CI" |
|
PR_Github #16570 [ skip ] triggered by Bot |
|
PR_Github #16570 [ skip ] completed with state |
5 participants
Summary by CodeRabbit
Description
In
docs/source/blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.mdthe imagenvcr.io/nvidia/tensorrt-llm/release:1.1.0rc0is used. By following the instructions one will get the errorThis is already resolved in PR6800 (https://github.com/NVIDIA/TensorRT-LLM/pull/6800/files) which is merged in rc1
By changing
nvcr.io/nvidia/tensorrt-llm/release:1.1.0rc0tonvcr.io/nvidia/tensorrt-llm/release:1.1.0rc1the example works again.Test Coverage
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.