[TRTLLM-9911] [doc] Update Perf-Overview.md for Release 1.2

[zbpatel]

This MR updates the performance overview documentation based on the results of the performance testing done for the 1.2 release. Performance benchmarking was conducted by @flin3500

Status:

• Started making updated based on 1.2 methodology changes (new gpus)
• TODO: update perf-tables with new results
• TODO: validate command / config changes with @flin3500

Summary by CodeRabbit

• Documentation
  • Updated performance overview documentation to include newly supported hardware variants: B300 and GB300
  • Expanded model compatibility lists with additional FP4 and FP8 quantized variants covering Kimi-K2, DeepSeek-R1, Qwen3, and Llama models
  • Added recommendations for CPU Affinity configuration when using NUMA systems

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

• Update tava architecture diagram if there is a significant design change in PR.

• 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

To see a list of available CI bot commands, please comment /bot help.

[coderabbitai]

📝 Walkthrough

Walkthrough

Documentation update to the performance overview guide adding CPU Affinity configuration guidance, hardware variants (B300, GB300), and expanding model lists with six FP4 and five FP8 model entries.

Changes

Cohort / File(s)	Summary
Documentation Updates docs/source/developer-guide/perf-overview.md	Added NUMA CPU Affinity configuration note, expanded hardware variants to include B300 and GB300, and extended FP4 and FP8 model lists with additional model entries.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~5 minutes

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description provides initial context about updates for release 1.2 but lacks detailed explanations in key template sections.	Complete the Description section with what was changed and why, fill in Test Coverage with relevant tests, and resolve TODO items or move PR to draft until ready for review.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Title check	✅ Passed	The title accurately reflects the main change: updating performance overview documentation for Release 1.2.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment

---

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

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@docs/source/developer-guide/perf-overview.md`:
- Line 41: Update the GB300 entry to include its memory capacity for consistency
with the other GPU lines: locate the line containing "GB300 (GB300 NVL72)" and
replace it with the same label plus the correct memory size (e.g., "GB300 192GB
(GB300 NVL72)"), ensuring the format matches other entries like "B300 288GB" and
"GB200 192GB".

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 6e59fe65-b728-481a-8bad-004fabb98f62

📥 Commits

Reviewing files that changed from the base of the PR and between 21796cd and 569350e.

📒 Files selected for processing (1)

• docs/source/developer-guide/perf-overview.md

[coderabbitai]

⚠️ Potential issue | 🟡 Minor

Add memory specification for GB300 to maintain consistency.

All other GPU entries in the hardware list include memory capacity (e.g., "B300 288GB", "GB200 192GB"), but the GB300 entry is missing this specification. Please add the memory size to maintain format consistency.

📝 Suggested fix

-- GB300 (GB300 NVL72)
+- GB300 {MEMORY_SIZE}GB (GB300 NVL72)

Replace {MEMORY_SIZE} with the appropriate memory capacity for GB300.

🤖 Prompt for AI Agents

Verify each finding against the current code and only fix it if needed.

In `@docs/source/developer-guide/perf-overview.md` at line 41, Update the GB300
entry to include its memory capacity for consistency with the other GPU lines:
locate the line containing "GB300 (GB300 NVL72)" and replace it with the same
label plus the correct memory size (e.g., "GB300 192GB (GB300 NVL72)"), ensuring
the format matches other entries like "B300 288GB" and "GB200 192GB".

[zbpatel]

/bot skip "doc update"

[github-actions]

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) --high-priority]

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.

--high-priority (OPTIONAL) : Run the pipeline with high priority. This option is restricted to authorized users only and will route the job to a high-priority queue.

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.

[zbpatel]

/bot skip --comment "doc update"

[tensorrt-cicd]

PR_Github #38639 [ skip ] triggered by Bot. Commit: 407c2ed Link to invocation