[test] nothing

[chunxiaozheng]

kv cache

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[robertgshaw2-redhat]

very nice!

[njhill]

We already have a --cpu-offloading-gb for offloading model weights... we should use more specific naming for these args to disambiguate.

[maobaolong]

@chunxiaozheng I suggest to use --enable-kvcache-cpu-offloading

[chunxiaozheng]

Good idea. I have updated.

[mergify]

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @chunxiaozheng.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

[eryugey]

This should be "blocks_to_swap_out_buffer" ?

[maobaolong]

Agree, @chunxiaozheng this maybe an accident typo?

[chunxiaozheng]

fixed.

[jiawei-liang]

hello,i want to know , can this solution run on 1-cpu/n-gpu in one host situtation?

[mergify]

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @chunxiaozheng.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork