refactor: remove batch_manager::KvCacheConfig and use executor::KvCacheConfig instead

[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 #9552 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #9552 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7011 completed with status: 'FAILURE'

[Funatiq]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #9555 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #9555 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7014 completed with status: 'FAILURE'

[Funatiq]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #9570 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #9570 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7028 completed with status: 'FAILURE'

[Funatiq]

/bot run

[tensorrt-cicd]

PR_Github #9583 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #9583 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7039 completed with status: 'FAILURE'

[Funatiq]

/bot run

[tensorrt-cicd]

PR_Github #9588 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #9588 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7043 completed with status: 'FAILURE'

[Funatiq]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #9679 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #9679 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7114 completed with status: 'FAILURE'

[Funatiq]

/bot run

[tensorrt-cicd]

PR_Github #9731 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #9731 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7165 completed with status: 'SUCCESS'

[Copilot]

Pull Request Overview

This PR centralizes the KvCacheConfig type by removing the old batch_manager::KvCacheConfig and using executor::KvCacheConfig, while also adding a new use_uvm option and updating serialization, Python bindings, and tests.

• Swapped includes and using aliases to use executor::KvCacheConfig throughout C++ code.
• Introduced a new use_uvm flag in both Python and C++ APIs, with updated pickle and serialization logic.
• Removed the legacy kvCacheConfig.h and its Python binding tests, updating unit tests to cover the new fields.

Reviewed Changes

Copilot reviewed 18 out of 18 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
triton_backend/inflight_batcher_llm/src/model_instance_state.h	Updated include path to use executor.h
tests/unittest/bindings/test_bindings_ut.py	Removed legacy KvCacheConfig pickle test
tensorrt_llm/llmapi/llm_args.py	Added use_uvm field to LLM API args model
tensorrt_llm/_torch/pyexecutor/resource_manager.py	Pointed KvCacheConfigCpp import to bindings.executor
cpp/tests/unit_tests/executor/serializeUtilsTest.cpp	Extended serialize test to cover partial reuse and use_uvm
cpp/tensorrt_llm/pybind/executor/executorConfig.cpp	Updated pickle getstate/setstate and constructor binding
cpp/tensorrt_llm/pybind/bindings.cpp	Removed old batch_manager::KvCacheConfig binding block
cpp/tensorrt_llm/executor/serialization.cpp	Added serialization/deserialization of enablePartialReuse, copyOnPartialReuse, useUvm
cpp/tensorrt_llm/executor/kvCacheConfig.cpp	Expanded constructor and methods to include useUvm
cpp/tensorrt_llm/batch_manager/trtGptModelInflightBatching.h/cpp	Switched to executor::KvCacheConfig and updated getters
cpp/tensorrt_llm/batch_manager/transformerBuffers.cpp	Qualified CacheType references after alias removal
cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp	Updated to use executor::KvCacheConfig getters including useUvm
cpp/include/tensorrt_llm/executor/executor.h	Extended KvCacheConfig class signature with useUvm
cpp/include/tensorrt_llm/batch_manager/transformerBuffers.h	Removed obsolete kvCacheConfig.h include
cpp/include/tensorrt_llm/batch_manager/kvCacheType.h	Added new CacheType enum header
cpp/include/tensorrt_llm/batch_manager/kvCacheManager.h	Updated function signatures to accept executor::KvCacheConfig
cpp/include/tensorrt_llm/batch_manager/kvCacheConfig.h	Deleted legacy config header

Comments suppressed due to low confidence (1)

tests/unittest/bindings/test_bindings_ut.py:405

• The previous test for KvCacheConfig pickling was removed, but no new test covers the updated executor.KvCacheConfig including the new use_uvm field. Consider adding a unit test to verify that pickle round-trip preserves all fields (enable_block_reuse, partial reuse flags, and use_uvm).

def test_Mpicomm():

[Funatiq]

/bot run

[tensorrt-cicd]

PR_Github #9854 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #9854 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #7268 completed with status: 'FAILURE'

[Funatiq]

/bot run

[tensorrt-cicd]

PR_Github #9893 [ run ] triggered by Bot

[achartier]

lgtm

[tensorrt-cicd]

PR_Github #9893 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7301 completed with status: 'FAILURE'

[Funatiq]

/bot run

[tensorrt-cicd]

PR_Github #9978 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #9978 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7361 completed with status: 'FAILURE'

[Funatiq]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #10019 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #10019 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #7391 completed with status: 'SUCCESS'