AI 智能体
model-serving
更新于 2026-11-05
Model Serving 工程规则
Model serving rules: pinned model revisions and measured latency budgets
- 技术栈
- Model Serving
- 主题
- 工程基线
- 条目
- 9 条
- 版本
- v0.2.0
✓ 应当这么做
- ✓ Bootstrap a host with a single idempotent script or image, not interactive steps
- ✓ Expose the smallest possible port surface and pin TLS configuration
- ✓ Keep runtime configuration in versioned files under the operator account
✕ 常见反模式
- ✕ Password logins on public SSH endpoints
- ✕ Ad-hoc firewall openings that are never reverted
- ✕ Configuration edited in place without a backup copy
◎ 交付前验证
- ◎ Rebuild the host from the bootstrap path at least once
- ◎ Port scan matches the intended surface
- ◎ Backups restored successfully into a scratch environment
同分类条目
42 篇AI 智能体
Vector Search 工程规则
Vector search rules: chunking strategy, recall evaluation and index rebuild path
AI 智能体
Feature Store 工程规则
Feature store rules: point-in-time correctness and train/serve parity
AI 智能体
Agent Skill Design 工程规则
Skill design rules: narrow triggers, explicit boundaries and verifiable outputs
AI 智能体
Agent Tool Calls 工程规则
Tool-call rules: server-side authorisation and deny-by-default allow-lists
AI 智能体
Agent Memory 工程规则
Memory rules: scoped retrieval, expiry and user-visible deletion
AI 智能体
RAG Retrieval 工程规则
RAG rules: citation-grade retrieval and evaluated recall before shipping