Paper

Beyond Prediction: Tail-Aware Scheduling for LLM Inference

Unreadunread

AI summary

arXiv:2606. 18431v1 Announce Type: new Abstract: LLM serving exhibits extreme length variability, making size-based scheduling difficult in practice.

Reading status

Priority

About this paper

Authors: Yueying Li, Yuanfan Chen, Jiayang Chen, Esha Choukse, Haoran Qiu, G. Edward Suh, Rodrigo Fonseca, Ziv Scully, Udit Gupta
Released: 2026-06-18 (21d ago)
Topic: Related to current project
Relation to my work: Read next because Beyond Prediction: Tail-Aware Scheduling for LLM Inference overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, under, soft, eval, source, line, rate, control. Source: arxiv cs.LG (Machine Learning).
arXiv: 2606.18431

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Beyond Prediction: Tail-Aware Scheduling for LLM Inference. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.