Measured-only placement planner for worker pools (sie_placement)

オープン
#903 コメント 4 件 リアクション 0 件 担当者 0 名 GitHub で見る

メンテナーはふだん 1 日以内に返信

まだ誰も着手していません。

評価

難易度
5/5
見積もり時間
1週間以上
初心者へのやさしさ
25/100
issue の種類
機能追加
明瞭さ
おおむね明確
活発さ
活発
技術スタック
helm, kubernetes, python

調査の方向性

Start by reading the workspace package layout and the existing worker pool, Helm chart, and KEDA trigger definitions; the issue names no specific files or tests. The proposed work spans versioned measurement schemas, a placement planner, a tuner, GPU availability, Helm output, an API applier, and chart integration. Done means delivering these in the eight staged pull requests while keeping the gateway pool specification and chart KEDA triggers unchanged.

索引モデルが issue の本文から書いたものです。

説明

Problem

Operators size worker pools by hand today. A Helm worker pool per machine profile, minReplicas, the pool warm floor (minimum_worker_count) and pinned_models decide which models run on which GPUs and which stay warm. Each choice trades three things: how long a request waits after a model has been idle, what the warm capacity costs, and how fast the model answers once warm. Nothing in the repository states the target for those three or derives a pool layout from measurements.

Proposal

Add a measured-only placement planner as a new workspace package, sie_placement, standard library only, not published to PyPI at first.

  • Input documents, versioned JSON. Per served identity (a model id or model:profile) they hold a come-alive p95, a warm p99 (time to first token and inter-token latency for generation) and a queue-wait p99, with optional named tiers. Receipts are throughput and latency measurements per identity on a machine profile and the GPU product the measurement actually ran on. The other documents are boot evidence, a price list per machine profile, and hourly demand.
  • Planner core, a pure function. It keeps only measured cells that meet the warm bound, picks the cheapest warmth that meets the come-alive bound, and emits a plan with a per-lane envelope (floor, buffer and scale-down window ranges). Its report gives the cost of each service level, the next cheaper option and the bound that blocks it, and ranked measurements worth taking. Cells without measurements are never chosen.
  • Tuner step, a pure function that keeps a lane's floor inside its envelope from live queue signals.
  • Optional pieces: a plan-to-Helm-values emitter, a sie-placement tune applier that moves a lane's warm floor inside its envelope through an API logical pool, and an opt-in chart workload for it.

The gateway's pool specification and the chart's KEDA triggers do not change.

Delivery

Eight stacked pull requests: schemas, planner core, tuner step, GPU availability, several models on one GPU, Helm values, the applier, and chart integration.

主要言語
Python
スター
3.5k
フォーク
328
平均マージ
16時間 25分
マージ済み PR(30日)
121

環境構築

このプロジェクトには開発コンテナ、Dockerfile、コントリビューションガイドがありません。まず README を読み、一般的な手順ははじめてのコントリビューションガイドを参照してください。

はじめの一歩

  1. issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
  2. 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
  3. リポジトリをフォークし、ブランチを切って変更します。
  4. issue 番号を参照したプルリクエストを送ります。

superlinked/sie のほかの issue

superlinked/sie の issue をすべて見る

似ている issue

Python の issue をもっと見る

新しい issue をメールで受け取る

初心者向けの GitHub issue を短くまとめたダイジェスト。