docs: split Phase 12 and Phase 13 into separate design documents
- docs/12-continuous-batching.md: scheduler, sequence management, batching strategy (currently single-request, expandable) - docs/13-http-api.md: HTTP server, OpenAI-compatible API, axum architecture, SSE streaming (TODO) Phase 12 = WHAT to compute (scheduling decisions) Phase 13 = HOW to expose it (HTTP protocol layer) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
101
docs/12-continuous-batching.md
Normal file
101
docs/12-continuous-batching.md
Normal file
@@ -0,0 +1,101 @@
|
||||
# Phase 12: Continuous Batching + Request Scheduler — Design Document
|
||||
|
||||
## Goal
|
||||
|
||||
实现 iteration-level 请求调度器,支持多请求并发执行和动态 batch 管理。这是 LLM serving 系统的核心调度逻辑。
|
||||
|
||||
## 核心概念
|
||||
|
||||
### Static Batching vs Continuous Batching
|
||||
|
||||
**Static(朴素)**:
|
||||
```
|
||||
Batch 1: [req1, req2, req3] → 等所有完成才开始下一批
|
||||
问题: req1 10 token 就完了,req3 要 200 token → req1 的 slot 空转
|
||||
```
|
||||
|
||||
**Continuous(本阶段目标)**:
|
||||
```
|
||||
Iteration 1: [req1, req2, req3] → req1 完成! slot 释放
|
||||
Iteration 2: [req2, req3, req4] → req4 立即填入
|
||||
每一个 iteration(一次 forward pass)重新决定哪些请求参与
|
||||
```
|
||||
|
||||
## 核心组件
|
||||
|
||||
### Sequence
|
||||
|
||||
```rust
|
||||
pub struct Sequence {
|
||||
pub id: SeqId,
|
||||
pub prompt_tokens: Vec<u32>,
|
||||
pub generated_tokens: Vec<u32>,
|
||||
pub status: SequenceStatus,
|
||||
pub sampling_params: SamplingParams,
|
||||
pub kv_cache_handle: KVCacheHandle, // 该 seq 的 KV cache 资源
|
||||
pub arrival_time: Instant,
|
||||
pub output_sender: tokio::sync::mpsc::Sender<GenerateEvent>,
|
||||
}
|
||||
|
||||
pub enum SequenceStatus {
|
||||
Waiting, // 等待调度
|
||||
Prefilling, // 正在 prefill
|
||||
Decoding, // 正在逐 token decode
|
||||
Finished, // 完成 (EOS / max_len)
|
||||
}
|
||||
```
|
||||
|
||||
### Scheduler
|
||||
|
||||
```rust
|
||||
pub struct Scheduler {
|
||||
waiting: VecDeque<Sequence>, // 等待队列
|
||||
running: Vec<Sequence>, // 正在执行
|
||||
max_batch_size: usize, // 最大并发数
|
||||
block_manager: BlockManager, // KV cache 资源管理
|
||||
}
|
||||
```
|
||||
|
||||
### 调度循环
|
||||
|
||||
```rust
|
||||
loop {
|
||||
// 1. 回收已完成的 sequence,释放 KV cache
|
||||
// 2. 从 waiting 中 admit 新请求(如果有空位+显存)
|
||||
// 3. 对 running 中的所有 seq 做一步 forward
|
||||
// - 新加入的做 prefill
|
||||
// - 已在运行的做 decode
|
||||
// 4. 对每个 seq 的 logits 做 sampling
|
||||
// 5. 发送新 token / 完成信号
|
||||
}
|
||||
```
|
||||
|
||||
## 当前状态 (Phase 12 初版)
|
||||
|
||||
当前实现是 **单请求顺序执行**(max_batch_size=1),是 continuous batching 的退化形式:
|
||||
- 一次只处理一个请求
|
||||
- 完成后才接受下一个
|
||||
- 无 preemption、无 batching
|
||||
|
||||
这是合理的起步——先跑通单请求 E2E,后续扩展为真正的并发 batching。
|
||||
|
||||
## 后续扩展 (Phase 15+)
|
||||
|
||||
1. **多请求 batch forward**: 将多个 seq 的 token 拼接为一个 batch 输入
|
||||
2. **Prefill-Decode 分离**: prefill (compute-bound) 和 decode (memory-bound) 分开调度
|
||||
3. **Preemption**: 显存不足时暂停低优先级 seq
|
||||
4. **动态 batch size**: 根据 KV cache 使用量调整
|
||||
|
||||
## Test Plan
|
||||
|
||||
- [x] 单请求 E2E: 提交请求 → 收到 token 流 → 完成信号
|
||||
- [ ] (后续) 多请求并发: 提交多个请求,验证都能正确完成
|
||||
- [ ] (后续) 短请求完成后新请求立即加入
|
||||
|
||||
## Takeaways
|
||||
|
||||
1. **单请求是 continuous batching 的特殊情况 (batch_size=1)**:当前实现的 engine 循环已经是正确的调度结构——receive request → prefill → decode loop → done → next request。扩展为多请求只需在 decode loop 中处理多个 sequence。
|
||||
|
||||
2. **Engine 在独立 OS thread 上跑是正确的设计**:GPU 操作是同步阻塞的(cudaDeviceSynchronize),如果放在 tokio runtime 中会 block 整个 async runtime。独立线程 + channel 通信是标准模式。
|
||||
|
||||
3. **std::sync::mpsc::SyncSender(capacity=1) 实现了天然的背压**:当 engine 忙时,新请求会 block 在 channel send 上,不会积压。
|
||||
Reference in New Issue
Block a user