[None][chore] expose tokens_per_block into KvCacheConfig

[Superjomn]

PR title

Please write the PR title by following template:

[JIRA ticket link/nvbug link/github issue link][fix/feat/doc/infra/...] <summary of this PR>

For example, assume I have a PR hope to support a new feature about cache manager of Jira TRTLLM-1000 ticket, it would be like

[TRTLLM-1000][feat] Support a new feature about cache manager

Description

Please explain the issue and the solution in short.

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 [--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.

Summary by CodeRabbit

• New Features

  • Added a tokens_per_block option in KV cache settings (default: 64) to control tokens per block; value is applied at runtime when provided.

• Refactor

  • Streamlined executor configuration: tokens_per_block is no longer exposed via executor configuration and is now managed through KV cache settings.

[Superjomn]

/bot run

[tensorrt-cicd]

PR_Github #11538 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #11538 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8541 completed with status: 'FAILURE'

[QiJune]

LGTM

[Superjomn]

/bot run

[tensorrt-cicd]

PR_Github #11605 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #11605 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8599 completed with status: 'FAILURE'

[Superjomn]

/bot run

[tensorrt-cicd]

PR_Github #11710 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #11710 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8666 completed with status: 'FAILURE'

[Superjomn]

/bot run

[tensorrt-cicd]

PR_Github #11760 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #11760 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8711 completed with status: 'FAILURE'

[Superjomn]

/bot run

[Superjomn]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #17760 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #17760 [ run ] completed with state DISABLED
L0 testing is limited to prioritized users. User Superjomn is not in the prioritized list. L0 testing cannot be triggered.

[richardhuo-nv]

/bot run --disable-fail-fast

[pcastonguay]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #17788 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #17788 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #13318 completed with status: 'FAILURE'

[Superjomn]

/bot run

[tensorrt-cicd]

PR_Github #17830 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #17830 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #13347 completed with status: 'FAILURE'

[pcastonguay]

/bot run

[tensorrt-cicd]

PR_Github #17890 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #17890 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #13399 completed with status: 'FAILURE'

[pcastonguay]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #17893 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #17893 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #13402 completed with status: 'FAILURE'

[pcastonguay]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #17932 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #17932 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #13439 completed with status: 'FAILURE'

[pcastonguay]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #17951 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #17951 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #13454 completed with status: 'SUCCESS'