Skip to content
View original post on X: LMSYS OrgOfficial
Published
22/100

LinkedIn describes serving an ads ranker with SLM and SGLang

AIXianxing Zhang explains how LinkedIn serves its ads ranker at more than 10K QPS with under 80 ms scoring latency. The post uses SLM and SGLang for the serving stack.
LMSYS OrgVerified on XOfficial
@lmsysorg
View on X

Part of a thread · earlier post

1 | @LinkedIn
Ads Ranking with SLM and SGLang at LinkedIn

Xianxing Zhang on serving an ads ranker at 10K+ QPS with under 80 ms scoring latency.

Source details

LMSYS Org · x.comPublished

Original title: 1 | @LinkedIn