Skip to content

[None][feat] Integrate KVCMv2 commit_min_snapshot in runtime#16185

Draft
jiaganc wants to merge 2 commits into
NVIDIA:mainfrom
jiaganc:codex/integrate-commit-min-snapshot-main
Draft

[None][feat] Integrate KVCMv2 commit_min_snapshot in runtime#16185
jiaganc wants to merge 2 commits into
NVIDIA:mainfrom
jiaganc:codex/integrate-commit-min-snapshot-main

Conversation

@jiaganc

@jiaganc jiaganc commented Jul 9, 2026

Copy link
Copy Markdown
Collaborator

@coderabbitai summary

Description

Integrate commit_min_snapshot support for SSM reuse from #15752 and connect it to the KV cache manager V2 block-reuse policies.

The cache manager now commits a minimal SSM snapshot when block reuse is enabled for policies other than all_reusable, propagates partial-reuse configuration, and handles the final context commit path. The change includes coverage for SSM/SWA reuse, partial-page commits, cache statistics, DeepSeek V4 sparse cache configuration, and V2 reuse-policy selection.

Test Coverage

  • Pre-commit hooks passed for both commits.
  • python3 -m py_compile passed for the directly modified Python implementation and test files.
  • Targeted pytest files were not run locally because the current environment does not have pytest installed.

PR Checklist

Please review the following before submitting your PR:

  • PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

  • PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

  • Test cases are provided for new code paths (see test instructions)

  • If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

  • Any new dependencies have been scanned for license and vulnerabilities

  • CODEOWNERS updated if ownership changes

  • Documentation updated as needed

  • Update tava architecture diagram if there is a significant design change in PR.

  • The reviewers assigned automatically/manually are appropriate for the PR.

  • Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

jiaganc added 2 commits July 9, 2026 00:55
Signed-off-by: Jiagan Cheng <jiaganc@nvidia.com>
Signed-off-by: Jiagan Cheng <jiaganc@nvidia.com>
@jiaganc jiaganc changed the title [None][feat] Add commit min snapshot for SSM reuse [None][feat] Integrate KVCMv2 commit_min_snapshot in runtime Jul 9, 2026
@jiaganc

jiaganc commented Jul 9, 2026

Copy link
Copy Markdown
Collaborator Author

This PR depends on #15752 and should wait for it to be merged first.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant