[Perf] Early return in KVCacheManager.allocate_slots

[Jialin]

Purpose

As the title, early return in KVCacheManager.allocate_slots to speed up scheduling, as most of the requests only allocate a block every 16 steps.

Test Plan && Test Result

With the change, we could observed allocate slots cost is cut by half from 17.24% to 8.24% over the total runtime (with async scheduling enabled)

Total runtime distribution for allocate_slots per engine step

Public benchmarks

• Before: 171.53s
• After: 165.90s (~3.3% total runtime reduction)

vllm bench latency --model facebook/opt-125m \
  --dtype bfloat16 \
  --batch-size 3000 \
  --input-len 128 \
  --output-len 1800 \
  -tp 1 \
  --num-iters-warmup 1 \
  --num-iters 3

---

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan, such as providing test command.
• The test results, such as pasting the results comparison before and after, or e2e results
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
• (Optional) Release notes update. If your change is user facing, please update the release notes draft in the Google Doc.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[chatgpt-codex-connector]

Skipped sliding-window cleanup when no new blocks allocated

allocate_slots now returns early when num_blocks_to_allocate==0 and no prefix-cache hits, so coordinator.remove_skipped_blocks() is never called on those steps. For sliding-window/ChunkedLocal attention this call is what frees blocks that have fallen outside the window; skipping it leaves those blocks held until the request hits a block boundary or finishes, inflating block_pool usage and causing unnecessary evictions or scheduling failures for long prompts that keep generating within an existing block.

Useful? React with 👍 / 👎.