Design resource-vector and provider-aware admission policies
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 5/5
- 预计耗时
- 一周以上
- 新手友好度
- 35/100
- Issue 类型
- 功能
- 描述清晰度
- 描述清楚
- 活跃度
- 冷清
- 技术栈
- python
调研方向
从 PR #658 以及 issue 中提到的 plans/645 文档开始，尤其是 task-admission.md、request-admission.md、capacity-model.md、observability.md、benchmark-plan.md 和 issue-map.md。产出一份已接受的设计文档或计划更新，记录未决问题、被拒绝的替代方案、后续实现 issue，以及所需的 liveness、fairness、遥测和基准测试证据；不要实现 resource vectors。
由索引模型根据 Issue 内容生成。
描述
Priority Level
Low
Epic: #645
Depends on: #641, #646, #644, #657, #649, #650
Related: #647, #648, #654
Target branch: epic/645-async-scheduling while the epic is active.
Source of Truth
Specification details live in PR #658 under plans/645/, especially task-admission.md, request-admission.md, capacity-model.md, observability.md, benchmark-plan.md, and issue-map.md. This issue tracks the design-spike slice and gates only.
Design Scope
Produce a decision-ready design for future resource-vector and provider-aware task-admission policies. This issue is design-only unless a follow-up implementation issue is explicitly created.
This issue owns:
- deciding whether resource-vector internals stay scheduler-internal or require any public metadata additions beyond #641;
- the minimal
SchedulerResourceKey/SchedulerResourceRequestshape for a later implementation; - mapping resolved metadata from #641/#646 into scheduler resource requests without exposing scheduler internals as plugin API;
- defining how task-stage provider/model awareness avoids duplicating request-stage AIMD admission from #657;
- defining how the accepted #650 bounded-borrow policy should carry forward from coarse task-stage resources into provider/model/resource-vector resources, including strict share, bounded solo prefill, peer-pressure yielding, and borrow-debt repayment semantics;
- defining per-generation-resource zero-inflight idle metrics for endpoint/GPU idleness evidence, including per-resource, total, max, and baseline-delta reporting;
- liveness, release/accounting, cancellation/error, telemetry, and benchmark requirements for a later implementation;
- recording rejected alternatives.
Quality Gates
- No resource-vector implementation lands as part of this design issue.
- The design preserves the task/request admission split and consumes request pressure only through read-only snapshots if needed.
- The design keeps
FairTaskQueueresponsible for ready ordering, not resource ownership. - The design explains whether bounded-borrow semantics remain policy-compatible once resource identity becomes provider/model/resource-vector aware, or explicitly records any required policy revision.
- The future implementation acceptance bar includes liveness, no permit leaks, multi-resource fairness tests, stale/retry/salvage behavior, correlated telemetry compatibility, and #649 benchmark evidence.
- Benchmark matrix covers asymmetric provider/model capacities, different dominant resources, neutral single-resource workloads, heavy-root compatibility, and correlated scheduler/request traces.
- Benchmark evidence must report per-generation-resource zero-inflight idle time: for each provider/model/resource, the total workflow wall time where that resource has no in-flight generation request while the workflow is still active. Reports should include per-resource idle, total idle, max idle, and deltas versus the named baseline.
Validation
Close with an accepted design document or plan update that cross-references plans/645, lists open questions, records rejected alternatives, and defines the exact follow-up implementation issue(s) and evidence gates.
- 主要语言
- Python
- 星标
- 2.3k
- 派生
- 227
- 平均合并
- 22 小时 51 分钟
- 30 天内合并 PR
- 61
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
NVIDIA-NeMo/DataDesigner 的其他 Issue
-
docs: required_columns description is incomplete for LLM and multimodal columns可能已有人在做 @nightcityblade 于 8 天前认领。 未关闭bug triaged
难度 2/5 1-3 小时 新手友好度 65/100
NVIDIA-NeMo/DataDesigner#1002 · 4 条评论 ·
维护者通常 1 天内回复
-
enforce \from future import annotations` via ruff FA102 rule`可能已有人在做 @chethanuk 于 36 天前认领。 未关闭task
难度 2/5 1-3 小时 新手友好度 82/100
NVIDIA-NeMo/DataDesigner#760 ·
维护者通常 1 天内回复
-
难度 5/5 一周以上 新手友好度 45/100
NVIDIA-NeMo/DataDesigner#1048 ·
维护者通常 1 天内回复
-
bug needs-discussion
难度 4/5 3-5 天 新手友好度 48/100
NVIDIA-NeMo/DataDesigner#1045 ·
维护者通常 1 天内回复
-
Structured-output parsing drops valid dictionary entries可能已有人在做 @nabinchha 今天认领。 未关闭bug
NVIDIA-NeMo/DataDesigner#1043 · 2 条评论 · 已指派 1 人 ·
维护者通常 1 天内回复
查看 NVIDIA-NeMo/DataDesigner 的全部 Issue
相似的 Issue
-
难度 2/5 1-3 小时 新手友好度 64/100
aws-samples/sample-per-model-bedrock#295 ·
维护者通常 1 天内回复
-
难度 1/5 1 小时以内 新手友好度 76/100
pyrevitlabs/pyRevit#3792 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 69/100
zephyrproject-rtos/reqmgmt#177 ·
-
难度 2/5 1-3 小时 新手友好度 78/100
polarsource/polar#15580 ·
维护者通常 1 天内回复
-
难度 1/5 1 小时以内 新手友好度 85/100
521xueweihan/HelloGitHub#4011 ·