[None][feat] Optimize CUDA graph memory usage for spec decode cases #6718
Conversation
Signed-off-by: Mike Iovine <[email protected]>
📝 WalkthroughWalkthroughThe changes update speculative decoding logic in the model engine and drafter. The condition for appending a draft length of 0 during CUDA graph warmup now checks if Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant ModelEngine
participant Drafter
User->>ModelEngine: Initialize / Warmup
ModelEngine->>Drafter: Check speculative config (max_concurrency)
alt max_concurrency is not None
ModelEngine->>ModelEngine: Append draft length 0
else max_concurrency is None
ModelEngine->>ModelEngine: Skip appending draft length 0
end
ModelEngine->>Drafter: Call should_use_spec_decode(requests)
Drafter-->>ModelEngine: Return True/False based on max_concurrency and request count
Estimated code review effort🎯 2 (Simple) | ⏱️ ~7 minutes Possibly related PRs
Suggested reviewers
Note ⚡️ Unit Test Generation is now available in beta!Learn more here, or try it out under "Finishing Touches" below. 📜 Recent review detailsConfiguration used: .coderabbit.yaml 📒 Files selected for processing (2)
🧰 Additional context used📓 Path-based instructions (2)**/*.py📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
Files:
**/*.{cpp,h,hpp,cc,cxx,cu,py}📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
Files:
🧠 Learnings (2)📚 Learning: 2025-07-17T09:01:27.402ZApplied to files:
📚 Learning: 2025-07-22T08:33:49.109ZApplied to files:
⏰ 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)
🔇 Additional comments (3)
✨ 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 comments)
Other keywords and placeholders
Documentation and Community
|
|
/bot run |
|
PR_Github #14507 [ run ] triggered by Bot |
|
PR_Github #14507 [ run ] completed with state |
…VIDIA#6718) Signed-off-by: Mike Iovine <[email protected]>
… cases (NVIDIA#6718)" This reverts commit 8df7a26.
… cases (NVIDIA#6718)" This reverts commit 8df7a26. Signed-off-by: Yilin Fan <[email protected]>
…VIDIA#6718) Signed-off-by: Mike Iovine <[email protected]>
Summary by CodeRabbit
Refactor
Documentation
Style
finaldecorator to prevent unintended method overrides.Description
There's no need to create two sets of CUDA graphs if speculation will never be turned off. If the user did not give us a
max_concurrencyin theirSpecConfig, theModelEnginecan just assume speculation is always on and skip creating "speculation off" CUDA graphs to save on memory.Test Coverage
Existing tests.
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.