refactor: decoding inputs

[Funatiq]

Description

Please see commit messages for details.

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 [--disable-fail-fast --skip-test --stage-list "A10-1, xxx" --gpu-type "A30, H100_PCIe" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-[Post-Merge]-1, xxx"]

Launch build/test pipelines. All previously running jobs will be killed.

--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 "A10-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-1, 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.

--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. Will also run 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-[Post-Merge]-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-[Post-Merge]-1, xxx".

For guidance on mapping tests to stage names, see docs/source/reference/ci-overview.md.

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.

[Funatiq]

/bot run

[tensorrt-cicd]

PR_Github #10670 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #10670 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #7894 completed with status: 'FAILURE'

[Funatiq]

/bot run

[tensorrt-cicd]

PR_Github #10814 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #10814 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #7988 completed with status: 'FAILURE'

[Funatiq]

/bot run

[tensorrt-cicd]

PR_Github #10834 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #10834 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #8004 completed with status: 'FAILURE'

[Funatiq]

/bot run

[tensorrt-cicd]

PR_Github #10853 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #10853 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #8020 completed with status: 'FAILURE'

[Funatiq]

/bot run

[tensorrt-cicd]

PR_Github #10974 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #10974 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8107 completed with status: 'FAILURE'

[Funatiq]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #11006 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #11006 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8131 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

[Copilot]

Pull Request Overview

This PR refactors how decoding inputs (especially generationSteps and speculative decoding data) are managed, moving state handling onto DecoderState and cleaning up deprecated fields.

• Moved generation_steps assignment from local decoding input objects to DecoderState via setter/getter.
• Removed inline speculative decoding setup functions in gptDecoderBatched.cpp and centralized them in batch manager.
• Updated Python bindings to expose generation_steps on DecoderState instead of the batch input struct.

Reviewed Changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
tensorrt_llm/_torch/pyexecutor/make_decoding_batch_input_output.py	Redirect generation_steps assignment to decoder_state setter
cpp/tensorrt_llm/runtime/gptDecoderBatched.cpp	Removed inline speculative‐decoding branches and generationSteps setup
cpp/tensorrt_llm/runtime/decoderState.cpp	Added getter/setter for generationSteps
cpp/tensorrt_llm/pybind/runtime/bindings.cpp	Exposed generation_steps property on DecoderState
cpp/tensorrt_llm/batch_manager/makeDecodingBatchInputOutput.cpp	Introduced shared set*Inputs helpers for speculative decoding modes
cpp/include/tensorrt_llm/runtime/iGptDecoderBatched.h	Removed outdated buffers includes; added config includes
cpp/include/tensorrt_llm/runtime/decodingInput.h	Cleaned up constructor definitions for EagleInputs
cpp/include/tensorrt_llm/runtime/decoderState.h	Declared new getGenerationSteps/setGenerationSteps methods

Comments suppressed due to low confidence (2)

cpp/tensorrt_llm/runtime/gptDecoderBatched.cpp:115

• The generationSteps field on dInput is no longer initialized here for beam search. You should restore setting dInput.generationSteps (e.g., when decoderState.getMaxBeamWidth() > 1) using the state’s stored steps so variable-beam search still works.

    dInput.batchSlots = input.batchSlots.at(step);

cpp/include/tensorrt_llm/runtime/iGptDecoderBatched.h:23

• [nitpick] This header isn’t referenced in the interface declared here. Consider removing the worldConfig.h include to reduce unnecessary dependencies.

#include "tensorrt_llm/runtime/worldConfig.h"