أربعة أوضاع تشغيل، وأي وضعين يمكنك استخدامهما اليوم
يتوفر وضعا Serverless وBatch الآن. أما Dedicated وPrivate فيتمان عبر المحادثة، وقول ذلك صراحةً أكثر فائدة من نموذج تسجيل لا يؤدي إلى شيء.
- تاريخ النشر
Grid runs inference in four modes. Two are available now and two are not, and it is worth being direct about which.
| Mode | What it is for | Availability |
|---|---|---|
| Grid Serverless | Elastic traffic. Capacity follows demand and scales to zero when idle. | Available |
| Grid Batch | Asynchronous inference at a discount, in controlled windows. | Available |
| Grid Dedicated | Committed capacity for steady production traffic. | Talk to us |
| Grid Private | An isolated environment for regulated workloads. | Talk to us |
Why "talk to us" rather than a waitlist#
Dedicated and Private both involve a commitment on our side: dedicated capacity, or an isolated environment with its own boundaries. Neither is something you can pick from a dropdown and have provisioned, and a form that implied otherwise would just move the conversation later, after you had already planned around it.
Serverless and Batch you can start on today. Run modes covers each in full, and access to Grid is invite only while we scale.