fix precompiled multi_query_token kernel not having is_fp8_out hash key

[jhaotingc]

Summary by CodeRabbit

Summary by CodeRabbit

• Bug Fixes
  • Improved kernel selection logic to correctly ignore the output format flag for precompiled kernels, preventing mismatches.
• Documentation
  • Added clarifying comments on the usage of the output format flag in kernel lookup for precompiled and JIT kernels.

Description

Llama 4 Maverick uses 40 attention head and 8 kv head.
This fails to use XQA mha_sm90.cu Hopper style spec-dec kernel due to 64 % (attention head / kv head) != 0.
This falls to precompiled XQA cubin kernel.
However precompiled does not support is_fp8_output flag in hashing key, causing not finding the kernel cubin.
This can be removed when it change to JIT.

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 the stage-list parameter 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.md
and the scripts/test_to_stage_mapping.py helper.

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.

[coderabbitai]

📝 Walkthrough

## Walkthrough

The changes update how the `is_fp8_output` flag is handled in hash key generation for XQA kernels. For precompiled kernels, the flag is now always set to false in the hash key, while for JIT kernels, the original value is used. Comments were added to clarify this logic.

## Changes

| File(s)                                                                 | Change Summary                                                                                   |
|-------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------|
| cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/decoderXQAImplCommon.cpp<br>cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/decoderXQAImplPrecompiled.cpp | Modified hash key generation to conditionally set `is_fp8_output` for precompiled vs JIT kernels; added explanatory comments. |

## Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

## Suggested reviewers

- lucifer1004  
- kaiyux

## Poem

> A hash key hops, a flag set anew,  
> For JIT, it keeps the value true.  
> But precompiled kernels, with logic tight,  
> Ignore FP8 and set it right.  
> With comments clear and code concise,  
> Review is quick—oh, isn’t that nice!  
> 🐇✨

Note

⚡️ Unit Test Generation is now available in beta!

Learn more here, or try it out under "Finishing Touches" below.

---

📜 Recent review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 60a65da and bb94b05.

📒 Files selected for processing (2)

• cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/decoderXQAImplCommon.cpp (1 hunks)
• cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/decoderXQAImplPrecompiled.cpp (1 hunks)

🚧 Files skipped from review as they are similar to previous changes (2)

• cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/decoderXQAImplPrecompiled.cpp
• cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/decoderXQAImplCommon.cpp

⏰ 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

✨ Finishing Touches

• 📝 Generate Docstrings

🧪 Generate unit tests

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

---

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Explain this complex logic.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai explain this code block.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and explain its main purpose.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR.
• @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
• @coderabbitai generate unit tests to generate unit tests for this PR.
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai or @coderabbitai title anywhere in the PR title to generate the title automatically.

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[jhaotingc]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #12661 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #12661 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #9414 completed with status: 'FAILURE'

[jhaotingc]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #12786 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #12786 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #9524 completed with status: 'FAILURE'

[jhaotingc]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #12885 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #12885 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #9604 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

[symphonylyh]

/bot reuse-pipeline

[tensorrt-cicd]

PR_Github #13047 [ reuse-pipeline ] triggered by Bot

[tensorrt-cicd]

PR_Github #13047 [ reuse-pipeline ] completed with state SUCCESS
Reusing PR_Github #12885 for commit bb94b05