runtime-reconfigurable disaggregation: x prefill workers feeding y decode workers, re-balanced live
xPyDobserved
| Value kind | observed — Reported measurements, counts, and specifications keep the precision and scope stated by their source; an exact specification is not treated as a range. |
|---|---|
| As of | 2026 |
| Source | NVIDIA Dynamo / TensorRT-LLM disaggregated serving docs · Runtime-Reconfigurable xPyD section; workers can be added and removed at runtime |
| Review | checking…review by 2026-11-23 · standard cadence |
| Recorded changes | last 2026-06-29 |
| Claim id | runtime-reconfigurable-disaggregation-x-prefill |
Where the guide uses it
← Full numbers register — every date-stamped figure in the guide, with revision history.