重點導讀
成熟的 AI 服務也可能在少見的使用情況下出錯,人工檢查不一定找得到。
- UCSD Hao AI Lab 正和 vLLM 團隊測試 vstack,用它檢查 vLLM 的程式行為。
- 目前找出 17 個錯誤,包含輸出內容悄悄出錯,以及伺服器無法繼續服務。貼文表示這些錯誤都有對應的修正提案,並挑出其中 5 個分享。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
Hao AI Lab@haoailab
·9 天前
(1/7) Agentic Formal Verification on vLLM 🚀
This week, we introduced vstack for agentic formal verification in AI infra; today, we're working with @vllm_project , putting vstack to test: although vLLM is already very mature, some bugs only surface in rare combinations that are hard for human reviewers to catch.
With vstack's agentic formal verification, we identified 17 (and growing!) bugs, from silent wrong output to server lockout. Below we share 5 of them, each with a fix PR ⬇️
🔌 vstack plugin: https://t.co/GZJebbjdpL
📋 Bugs Tracker: https://t.co/6f6WmtRUWU
推文來源 · X (Twitter)在 X 參與討論
來源: Hao AI Lab (x.com)
在 X 查看推文