Shopify 在 PyTorchCon 2026 分享基于 PyTorch 和 vLLM 的持续学习闭环
Shopify 在 PyTorchCon 分享生产级持续学习闭环：judge 抓坏输出，critic 修数据，小模型还能打赢前沿模型。
Shopify 工程师 Cody Mazza-Anthony 在 PyTorchCon 2026 上讲解如何用 PyTorch 和 vLLM 搭建持续学习流程。以 Buyer Profile 功能为例，校准后的 judge 会在生产环境中标记低分输出，critic 逐一诊断失败原因，带 critic 提示的重放结果再由 judge 重新打分，被采纳的修复会扩充训练数据。他还展示了小型专用模型在该任务上跑赢前沿模型的做法，并通过 prompt 压缩优化推理。
Now: '@Shopify’s continual learning loop with PyTorch and @vLLM_project takes the stage at #PyTorchCon 2026 with Cody Mazza-Anthony @cmazzaanthony.
Using Buyer Profile as an example, Cody walks through how a calibrated judge flags low-scoring outputs in production. Critics diagnose each failure, and a replay with a critic hint is scored again by the judge. Accepted repairs expand and improve the training data.
Cody shows how a small specialist model can outperform a frontier model on this task, then turns to optimizing inference through prompt compression.
Watch the keynote livestream: https://t.co/6TtaEkw0x7