feat: add priority based scheduling with priority based request acceptance and preemption (#8746)

This commit is contained in:
harrisonlimh
2025-09-16 17:10:10 -07:00
committed by GitHub
parent f949ad5794
commit 14fdd52740
16 changed files with 822 additions and 71 deletions

View File

@@ -125,6 +125,7 @@ class OpenAIServingEmbedding(OpenAIServingBase):
adapted_request = EmbeddingReqInput(
**prompt_kwargs,
rid=request.rid,
priority=request.priority,
)
return adapted_request, request