[None][refactor] Simplify finish reasons handling in DecoderState #6524
Conversation
… in gptDecoderBatched - Updated input and output finish reasons to use same tensor slice instead of multiple slices for different steps. Signed-off-by: Robin Kobus <[email protected]>
- Removed steps dimension from the shape of finished steps in DecoderState. - Updated the reshape logic in DecoderState to streamline buffer management and removed redundant reshaping of finished steps. - Updated gptDecoderBatched to use the new shape of finished steps. Signed-off-by: Robin Kobus <[email protected]>
- Removed the finished steps tensor from DecoderState and its associated methods. - Updated references in createNewDecoderRequests and gptDecoderBatched to use finish reasons instead of finished steps. - Adjusted bindings in both nanobind and pybind to reflect the removal of finished steps. Signed-off-by: Robin Kobus <[email protected]>
|
/bot run |
|
PR_Github #13704 [ run ] triggered by Bot |
Funatiq
changed the title
|
@coderabbitai review |
✅ Actions performedReview triggered.
|
📝 WalkthroughWalkthroughThe changes remove the Changes
Sequence Diagram(s)sequenceDiagram
participant Python API
participant DecoderState
participant Decoder Engine
Python API->>DecoderState: Create/Access DecoderState
Note right of DecoderState: (No longer exposes finished_steps)
Python API->>DecoderState: Access finishReasons
DecoderState->>Decoder Engine: Provide finishReasons tensor
Decoder Engine->>DecoderState: Update finishReasons as needed
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~15–20 minutes 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 (6)
💤 Files with no reviewable changes (2)
🧰 Additional context used🧠 Learnings (2)📓 Common learnings📚 Learning: in tensorrt-llm's multimodal processing pipeline, shared tensor recovery using `from_shared_tensor()...Applied to files:
🔇 Additional comments (6)
✨ 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. 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)
Other keywords and placeholders
Documentation and Community
|
|
PR_Github #13704 [ run ] completed with state |
|
/bot run --extra-stage "A30-TensorRT-Post-Merge-2, A30-TensorRT-Post-Merge-4, A30-TensorRT-Post-Merge-5, A30-TensorRT-Post-Merge-6" |
|
PR_Github #13803 [ run ] triggered by Bot |
|
PR_Github #13803 [ run ] completed with state |
Funatiq
changed the title
…IDIA#6524) Signed-off-by: Robin Kobus <[email protected]> Signed-off-by: Lanyu Liao <[email protected]>
…IDIA#6524) Signed-off-by: Robin Kobus <[email protected]>
3 participants
Summary by CodeRabbit
Description
FinishReasonper request for the different steps of draft-target speculative decoding.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.
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)]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.