From 00ba573631b8da3989a8e90f113f714a6c8d764d Mon Sep 17 00:00:00 2001 From: Gahow Wang Date: Mon, 29 Jun 2026 20:26:58 +0800 Subject: [PATCH] Document harness design contract --- docs/aituner-harness-design-contract.md | 307 ++++++++++++++++++++++++ docs/aituner-roadmap.md | 4 + 2 files changed, 311 insertions(+) create mode 100644 docs/aituner-harness-design-contract.md diff --git a/docs/aituner-harness-design-contract.md b/docs/aituner-harness-design-contract.md new file mode 100644 index 0000000..22ea509 --- /dev/null +++ b/docs/aituner-harness-design-contract.md @@ -0,0 +1,307 @@ +# AITuner Harness Design Contract + +本文总结当前 AITuner harness 的设计语义。它不是实验流水账,也不是最终论文文字; +它的作用是把我们能 claim 的系统贡献、各模块做法、隐含假设和限制说清楚。 + +核心结论: + +```text +AITuner harness 的贡献不是“LLM 会调参”,也不是“写了一组专家 if/else 规则”。 + +Harness 的目标是把 black-box knob search 转成: +measurement-grounded, mechanism-guided, validator-controlled experiments。 +``` + +换句话说,planner 可以是 LLM、BO、bandit、deterministic heuristic 或人工选择。 +Harness 负责把观测转换成可审计的机制假设,生成合法候选,并用真实测量验证或否定这些假设。 + +## 核心流程图 + +```mermaid +flowchart TD + A[StudySpec
engine schema, tunable knobs, hardware, SLO] --> B[Run trial / probe] + W[Workload window
prompt length, output length, arrivals, prefix/cache hints] --> C + B --> C[Observation schema
effective config, probe result, SLO violations, launch status] + C --> D[Evidence compiler
symptom evidence over serving stages] + D --> E[Mechanism hypotheses
prefill, decode, admission, memory, launch] + E --> F[Mechanism action families
topology, scheduler, concurrency, cache, frontier transfer] + F --> G[CandidateSet
legal patches + hypotheses + expected effects] + G --> H[Planner backend
LLM / BO / heuristic ranks candidates] + H --> I[Validator + materializer
constraints, no-repeat full config, failure memory, stop authority] + I --> B + B --> J[Measurement verdict
SLO pass, req/s/GPU, latency quantiles] + J --> C + G --> K[Stop decision
only when coverage and measurement guards allow] +``` + +关键点:LLM 不应该绕过 `CandidateSet` 和 `Validator`。LLM 最多是 candidate ranker 或 copilot, +不是 legality、coverage 或 stop 的 authority。 + +## 模块语义 + +### 1. Observation Schema + +Harness 先把一次 trial/probe 的结果转成结构化 observation: + +```text +O_t = { + workload summary, + SLO rules, + effective engine config, + best feasible probe, + limiting probe, + failed_reason_counts, + early_stop_reason, + pass_rate, + request_rate_per_gpu, + launch / OOM status +} +``` + +其中 `failed_reason_counts` 的定义是 request-level SLO violation reason 的 multiset 计数: + +```text +ttft_ms>threshold request 的 TTFT 超 SLO +tpot_ms>threshold request 的 TPOT 超 SLO +arrival_lag_s>limit synthetic arrivals 已经追不上 +probe_elapsed_s>limit probe 总耗时超过上限 +slo_pass_rate_unrecoverable + 已失败过多,数学上无法达到 target pass rate +request_failed / timeout / completion mismatch + 请求级失败 +``` + +重要限制: + +- 一个 request 可以同时贡献 `ttft_ms>...` 和 `tpot_ms>...`; +- `failed_reason_counts` 是 symptom evidence,不是 root-cause ground truth; +- queueing/admission 主要来自 probe 调度层 early stop,而不是单个 request latency 的精确分解。 + +因此文档和论文里必须避免说“failed count 证明 root cause 是 TTFT/TPOT”。更准确的说法是: + +```text +failed_reason_counts gives SLO violation symptoms. +Harness infers serving-stage hypotheses from these symptoms. +``` + +### 2. Evidence Compiler / Bottleneck Hypotheses + +当前 prototype 做两层聚合。 + +第一层是单个 probe 的 active bottleneck。当前实现用 count-majority: + +```text +ttft_count = sum(count(reason startswith "ttft")) +tpot_count = sum(count(reason startswith "tpot")) +other_request_failed_count = non-TTFT, non-TPOT request failures + +if ttft_count >= max(tpot_count, other_request_failed_count): + active = ttft_prefill +elif tpot_count >= max(ttft_count, other_request_failed_count): + active = decode_tpot +else: + active = admission_or_queueing +``` + +这一步是 heuristic。它的语义基础是 TTFT/TPOT/arrival-lag 对应不同 serving stages, +但 “majority label = root cause” 并不成立。 + +第二层是跨 trial 的 ranked hypotheses。它把以下证据合成 score: + +- workload prior:decode-only + TPOT SLO 更支持 decode hypothesis;长 prompt tail 更支持 prefill hypothesis; +- latest probe active label; +- historical probe evidence; +- `failed_reason_counts` 中 TTFT/TPOT/queueing symptom ratio; +- launch failure / OOM。 + +更稳健的目标设计应该把第一层 hard label 改成 soft evidence vector: + +```text +e_prefill = normalized count of TTFT symptoms +e_decode = normalized count of TPOT symptoms +e_admission = normalized count of arrival lag / elapsed / unrecoverable / request failures +e_memory = launch or OOM evidence +``` + +Candidate generator 应该基于 evidence distribution 生成 top mechanism probes,而不是只相信一个 +hard dominant bottleneck。当前 prototype 的 hard label 是工程近似,不是最终 contribution。 + +### 3. Mechanism Space + +Harness 不在 raw knob Cartesian product 中盲搜: + +```text +raw space = {TP, DP, EP, GMU, MNS, MBT, chunked-prefill, ...} +``` + +它先把 knobs 映射到 serving pipeline 上的可控 mechanism: + +| Mechanism family | Example knobs | 机制含义 | 典型 evidence | +| --- | --- | --- | --- | +| Topology / resource partition | TP, DP, EP, visible GPUs | 改变 compute/memory 分布、replica 数、per-GPU efficiency | TTFT/TPOT pressure, topology frontier 未覆盖 | +| Prefill scheduler | chunked prefill, MBT | 改变 prefill quantum 和 head-of-line blocking | TTFT symptoms, long prompt tail, low prefix reuse | +| Admission / concurrency | MNS | 改变活跃 sequence 数和 batch/admission pressure | arrival lag, pass-rate unrecoverable, concurrency underuse | +| KV/cache headroom | GMU, block/cache knobs | 改变 KV cache blocks 和 memory feasibility | cache pressure, launch/memory, topology settled 后仍有 SLO pressure | +| Launch/memory feasibility | env, memory-affecting flags | 确认 engine 是否能启动、是否 OOM | launch failure, OOM | +| Frontier delta transfer | measured runtime delta applied to other Pareto anchors | 将已测 runtime 改动投影到未测 frontier anchor | 同 topology 上 runtime delta 为正,且存在其他 Pareto anchor | + +这些 family 的依据不是某个 case 的 winning config,而是 LLM serving pipeline: + +```text +arrival/admission -> prefill -> decode -> memory/launch feasibility +``` + +每个 family 必须满足三条约束: + +1. 它对应一个可解释的 serving mechanism; +2. 它只生成 engine schema 和 hardware constraints 下合法的 candidate; +3. 它的 confirm/reject condition 由真实 measurement 决定。 + +限制: + +- Mechanism family 是 domain-specific,不是 engine-agnostic magic; +- vLLM/SGLang 等 engine 的 knob 名称不同,需要 adapter 把 engine knobs 映射到同一 mechanism vocabulary; +- family 本身有系统依据,但当前 score 常数和部分 gate 仍是 heuristic。 + +### 4. CandidateSet / Intervention Generation + +Candidate 不是“一个 patch”这么简单。一个合法 candidate 应包含: + +```text +candidate = { + mechanism_family, + config_patch, + hypothesis, + expected_effects, + confirm_condition, + reject_condition, + effective_full_config_signature +} +``` + +当前 prototype 的候选顺序大致是: + +1. topology candidates; +2. frontier-delta projection candidates; +3. runtime candidates。 + +其中 runtime candidates 又包含 prefill scheduler、MBT、MNS、GMU 等 family。 + +设计假设: + +- topology/resource partition 通常改变较大的 capacity frontier; +- runtime knobs 通常是同一 topology 下的 local refinement; +- 当 topology frontier 未覆盖时,过早 runtime hill-climbing 可能把搜索困在坏 topology; +- 当一个 runtime delta 已在某个 topology 上测得正收益时,把这个 delta 投影到其他 Pareto + anchor 是比完整 factorial grid 更便宜的 interaction test。 + +限制: + +- `topology-before-runtime` 是强 prior,不是定理;需要 ablation; +- frontier delta transfer 依赖已测 history,如果 history 太少就不能工作; +- 当前 prototype 中一些 target step 和 score 常数仍然是人工 heuristic。 + +### 5. Planner Interface + +Planner 的职责应该被限制为: + +```text +rank/select candidate from CandidateSet +explain why this candidate is worth the next trial +``` + +Planner 不应该: + +- 构造 schema 外的 knob; +- 绕过 topology / memory constraints; +- 重复已经测试过的 effective full config; +- 单方面决定 stop; +- 把自然语言猜测当成 measurement verdict。 + +这也是 no-LLM harness 能工作的原因:只要 `CandidateSet` 和 `Validator` 足够有信息, +一个 deterministic planner 也可以完成 tuning。LLM 的价值在于组合 evidence、解释 tradeoff、 +在候选较多时排序,而不是提供 tuning correctness 的唯一来源。 + +### 6. Validator / Stop Authority + +Validator 是 harness 防止 prompt engineering 化的关键。它负责: + +- canonicalize effective full config; +- 拒绝 no-op 或 repeat; +- 检查 legal topology / visible GPU / tunable schema; +- 记录 failure memory; +- 判断 measurement ceiling,例如 `search.high` 是否不足; +- 在 candidate coverage 不足时禁止 premature stop; +- 只有在覆盖和 measurement guards 都满足时授权 stop。 + +重要设计修正: + +```text +no-repeat must use normalized effective full-config signature, +not patch signature. +``` + +因为 runtime-only patch 在 materialization 时会继承 incumbent topology。 +如果只看 patch signature,可能把 `{"gmu": 0.9}` 误认为新 config, +但真实执行时它可能 materialize 成已测过的 full config。 + +限制: + +- Validator 只能保证相对于声明的 grammar/operator set 的 coverage; +- 它不能证明全 raw knob space 没有更优点; +- measurement ceiling 不足时应报告并请求人类确认,而不是静默合成 arrivals 或重复窗口。 + +## 精确贡献表述 + +我们应该 claim: + +```text +AITuner introduces a planner-agnostic harness that converts LLM serving +configuration tuning from black-box knob search into typed, measurement-grounded +counterfactual experiments over serving mechanisms. +``` + +可拆成三点贡献: + +1. **Serving-stage evidence compiler** + 将 workload profile、SLO violation symptoms、probe early stop 和 launch failure + 转换为 prefill/decode/admission/memory/launch 的机制证据,而不是只给 planner 一个 scalar score。 + +2. **Typed mechanism action space** + 将 raw knobs 组织为 topology、prefill scheduler、admission/concurrency、cache headroom、 + frontier transfer 等 intervention families,使搜索发生在 mechanism space 而不是任意 knob vector space。 + +3. **Validator-controlled experimental loop** + 用 full-config signature、constraints、failure memory、coverage 和 measurement guards + 控制 proposal 与 stop,使 LLM/BO/heuristic 都只能在合法、可审计的 candidate set 上工作。 + +我们不应该 claim: + +- bottleneck classifier 永远正确; +- `failed_reason_counts` 是 root cause label; +- 当前 heuristic score 常数有理论最优性; +- harness 覆盖完整 raw knob space; +- stop 证明全局最优; +- 某个 case 的 winning config 被系统“证明”出来。 + +## 必须补的证据 + +为了证明贡献不是 rule accumulation,后续实验必须 ablate family 和 authority,而不是只报最终性能: + +| Ablation | 证明什么 | +| --- | --- | +| classifier off / shuffled evidence | evidence attribution 是否真的影响正确方向 | +| mechanism space off,改用 raw random/BO | mechanism action space 是否压缩搜索并提升收敛 | +| topology-before-runtime off | 大 frontier intervention prior 是否必要 | +| frontier-delta projection off | cross-topology runtime transfer 是否解决 bad-start/local trap | +| validator off / patch signature only | full-config validator 是否避免重复和 false progress | +| no-LLM deterministic planner | harness 是否是 planner-agnostic substrate | +| weak planner + harness vs strong planner naive | harness 是否能补偿 planner 能力差距 | + +最终论文表达应保持这个边界: + +```text +Harness makes the search more structured, auditable, and measurement-efficient. +It does not replace measurement, does not prove global optimality, and does not +turn symptom labels into perfect causal diagnosis. +``` diff --git a/docs/aituner-roadmap.md b/docs/aituner-roadmap.md index 1adc4c7..273f8fe 100644 --- a/docs/aituner-roadmap.md +++ b/docs/aituner-roadmap.md @@ -64,6 +64,10 @@ kernel、KV cache、通信和排队的闭式性能模型。更稳妥也更强的 ## 关键设计点 +当前 harness 设计语义、模块假设和限制见 +[AITuner Harness Design Contract](aituner-harness-design-contract.md)。Roadmap 只维护 +claim 和实验优先级;design contract 负责精确定义我们能说什么、不能说什么。 + | 设计点 | 更强表述 | 作用 | 需要证明 | | --- | --- | --- | --- | | Observation | mechanism state | 将 workload shape、probe trace、SLO failure、launch/memory failure 结构化 | agent 看到的是可计算状态,不是自然语言日志 |