[None][doc] update moe support matrix for DS R1 #6883
Conversation
Signed-off-by: taoli <litaotju@users.noreply.github.com>
📝 WalkthroughWalkthroughUpdated the quick-start deployment guide to replace a Blackwell-specific NVFP4 note with a MoE Backend Support Matrix and guidance on default and explicit backend configuration. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes 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: 1
🧹 Nitpick comments (2)
docs/source/deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.md (2)
25-26: Tighten wording and fix grammar.Improve clarity and correctness (MoE expansion, singular/plural, extra space).
-There are multiple MOE backends inside TRT-LLM, not all of them supporting every precision on every GPUs. Here are the support matrix of the MOE backends. +There are multiple Mixture-of-Experts (MoE) backends within TensorRT-LLM; not all of them support every precision on every GPU. Here is the support matrix for MoE backends.
35-35: Clarify default behavior and give a concrete example reference.Minor grammar and add an example to anchor the guidance to the matrix.
-The default moe backend is `CUTLASS`, so for the combination which is not supported by `CUTLASS`, one must set the `moe_config.backend` explicitly to run the model. +The default MoE backend is `CUTLASS`. For combinations not supported by `CUTLASS`, explicitly set `moe_config.backend` (e.g., `backend: DEEPGEMM` on B200/GB200 FP8 per the table).
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
docs/source/deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.md(1 hunks)
🧰 Additional context used
🪛 LanguageTool
docs/source/deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.md
[grammar] ~27-~27: There might be a mistake here.
Context: ...e | Checkpoint | Supported moe_backend | |----------|----------|----------| | H10...
(QB_NEW_EN)
[grammar] ~28-~28: There might be a mistake here.
Context: ...end | |----------|----------|----------| | H100/H200 | FP8 | CUTLASS | | B200/GB2...
(QB_NEW_EN)
[grammar] ~29-~29: There might be a mistake here.
Context: ...---------| | H100/H200 | FP8 | CUTLASS | | B200/GB200 EP<=8 | NVFP4 | CUTLASS, TR...
(QB_NEW_EN)
[grammar] ~30-~30: There might be a mistake here.
Context: .../GB200 EP<=8 | NVFP4 | CUTLASS, TRTLLM | | B200/GB200 EP<=8 | FP8 | DEEPGEMM | | ...
(QB_NEW_EN)
[grammar] ~31-~31: There might be a mistake here.
Context: ... | | B200/GB200 EP<=8 | FP8 | DEEPGEMM | | GB200 NVL72 EP>8 | NVFP4 | WIDEEP | |...
(QB_NEW_EN)
[grammar] ~32-~32: There might be a mistake here.
Context: ...| | GB200 NVL72 EP>8 | NVFP4 | WIDEEP | | GB200 NVL72 EP>8 | FP8 | N/A (WIP) | ...
(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). (2)
- GitHub Check: Pre-commit Check
- GitHub Check: Analyze (python)
🔇 Additional comments (1)
docs/source/deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.md (1)
23-24: Section addition is helpful and well-placed.Introducing a MoE backend support matrix here improves discoverability for users configuring R1 deployment.
docs/source/deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.md
Show resolved
Hide resolved
litaotju
changed the title
|
/bot help |
|
/bot --help |
GitHub Bot Help
Provide a user friendly way for developers to interact with a Jenkins server. Run See details below for each supported subcommand.
Launch build/test pipelines. All previously running jobs will be killed.
kill
Kill all running builds associated with pull request. skip
Skip testing for latest commit on pull request. 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. |
1 similar comment
GitHub Bot Help
Provide a user friendly way for developers to interact with a Jenkins server. Run See details below for each supported subcommand.
Launch build/test pipelines. All previously running jobs will be killed.
kill
Kill all running builds associated with pull request. skip
Skip testing for latest commit on pull request. 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. |
Signed-off-by: taoli <litaotju@users.noreply.github.com> Co-authored-by: taoli <litaotju@users.noreply.github.com>
Signed-off-by: taoli <litaotju@users.noreply.github.com> Co-authored-by: taoli <litaotju@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
Signed-off-by: taoli <litaotju@users.noreply.github.com> Co-authored-by: taoli <litaotju@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
Signed-off-by: taoli <litaotju@users.noreply.github.com> Co-authored-by: taoli <litaotju@users.noreply.github.com>
Signed-off-by: taoli <litaotju@users.noreply.github.com> Co-authored-by: taoli <litaotju@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
Signed-off-by: taoli <litaotju@users.noreply.github.com> Co-authored-by: taoli <litaotju@users.noreply.github.com>
Signed-off-by: taoli <litaotju@users.noreply.github.com> Co-authored-by: taoli <litaotju@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
4 participants
Summary by CodeRabbit
Description
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.