iomgaa/PolyGateway
1
0
Fork 0
Code Issues 5 Pull Requests Actions Packages Projects Releases 17 Wiki Activity

docs: document net generation time and mid-stream stall hedging

Browse Source
This commit is contained in:
iomgaa
2026-09-14 02:13:55 -04:00
parent 2ac05a20b6
commit ca8743bf33
6 changed files with 182 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
research-wiki/ROADMAP.md
+2
View File
@@ -70,6 +70,8 @@
**已交付增补(2026-09-10)**: 长尾对冲(issue #24,1.3.7)——chat 单路并发对冲,触发=流式首 token 未至/非流式纯时长阈值,异源走完整准入,默认关闭;`CallStats` 增 `generation_ms`(裸生成时间)/`hedges`/`hedge_won`。设计 designs/2026-09-10-24-hedged-requests-design.md(人类已批准 H1-H8),实施 plans/2026-09-10-24-hedged-requests.md。后续储备:梯次多路对冲(H5 预留)、分位数触发、embedding/OCR 对冲(现不做)。
**已交付增补(2026-09-14)**: 流式中段沉默计量与对冲(issue #27/#28,1.3.8)——`generation_ms` 口径重定义为**净生成时间**(墙钟 − Σ超阈值中段沉默,仍含 TTFT 与尾部;1.3.7 墙钟口径由 `generation_ms + stall_ms` 还原,披露见 CHANGELOG 未发布段),`CallStats` 增 `stall_ms`/`stall_count` 归因字段,遥测表加同两列(INSERT 字段 36→38);`{SCOPE}__HEDGE__STALL_AFTER_S` 中段沉默对冲(独立于 `HEDGE__AFTER_S` 生效、默认关闭;无业界公开先例,超业界现状能力),`{SCOPE}__STREAM__STALL_THRESHOLD_MS` 计量阈值(默认 1000,三层可调)。设计 designs/2026-09-11-streaming-stall-design.md(人类已批准 + 独立审查补遗 B1-B4/N1-N9),实施 plans/2026-09-11-streaming-stall.md,验证 findings/2026-09-11-streaming-stall-validation.md。后续储备:自适应分位阈值(防反馈环,现不做)、流式透传下的 commit 点重审、embedding/OCR 对冲(现不做)。
## 7. 开放决策依赖
| 决策 | 阻塞点 | 需拍板时间 |