Optimize scheduler for chunk prefill

[liyonghua0910]

Motivation

💡 If this PR is a Cherry Pick, the PR title needs to follow the format by adding the [Cherry-Pick] label at the very beginning and appending the original PR ID at the end. For example, [Cherry-Pick][CI] Add check trigger and logic(#5191)

💡 如若此PR是Cherry Pick，PR标题需遵循格式，在最开始加上[Cherry-Pick]标签，以及最后面加上原PR ID，例如[Cherry-Pick][CI] Add check trigger and logic(#5191)

Modifications

Usage or Command

Accuracy Tests

Checklist

• Add at least a tag in the PR title.
  • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
  • You can add new tags based on the PR content, but the semantics must be clear.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
• Provide accuracy results.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

[paddle-bot]

Thanks for your contribution!

[PaddlePaddle-bot]

🤖 AI Code Review | 2026-04-17 11:01 CST

📋 Review 摘要

PR 概述：优化 chunk prefill 场景下 RUNNING 请求的调度策略，移除抢占逻辑，改为直接中断并阻止 WAITING 请求调度
变更范围：Scheduler 调度逻辑（resource_manager_v1.py）
影响面 Tag：Scheduler KVCache

📝 PR 规范检查

PR 标题缺少规范 Tag，描述中 Motivation 和 Modifications 部分未填写。

标题建议（可直接复制）：

• [Scheduler][Optimization] Optimize scheduler for chunk prefill

描述建议：请补充 Motivation（为什么需要此优化）和 Modifications（具体改了什么）。

问题

级别	文件	概述
🔴 Bug	resource_manager_v1.py:698	_get_can_schedule_prefill_threshold_block 调用缺少 request 参数，运行时会 TypeError
🔴 Bug	resource_manager_v1.py:702	allocate_gpu_blocks 多传了 request_id 参数，运行时会 TypeError

总体评价

调度策略优化方向合理，但存在两个方法调用参数不匹配的 Bug，均会导致运行时 TypeError 崩溃，需修复后才能合入。

[PaddlePaddle-bot]

🔴 Bug _get_can_schedule_prefill_threshold_block 方法签名为 (self, request, num_chunk_new_block)，需要两个参数，但这里只传了 num_new_block 一个参数，缺少 request。运行时会抛出 TypeError: _get_can_schedule_prefill_threshold_block() missing 1 required positional argument。

注意：同文件中 WAITING 请求调度部分（第762行、第810行）的调用是正确的，传了 (request, num_new_block) 两个参数。

建议修复：

can_schedule_block_num_threshold = self._get_can_schedule_prefill_threshold_block(request, num_new_block)

[PaddlePaddle-bot]

🔴 Bug allocate_gpu_blocks 方法签名为 (self, num_blocks)，只接受一个参数，但这里额外传入了 request.request_id。运行时会抛出 TypeError: allocate_gpu_blocks() takes 2 positional arguments but 3 were given。

注意：同文件中其他所有 allocate_gpu_blocks 调用（第620行、第633行、第648行、第662行、第768行、第816行）都只传了一个参数。

建议修复：

request.block_tables.extend(
    self.cache_manager.allocate_gpu_blocks(num_new_block)
)