REVIEW 2 cited by
InferLine: ML Prediction Pipeline Provisioning and Management for Tight Latency Objectives
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Serving ML prediction pipelines spanning multiple models and hardware accelerators is a key challenge in production machine learning. Optimally configuring these pipelines to meet tight end-to-end latency goals is complicated by the interaction between model batch size, the choice of hardware accelerator, and variation in the query arrival process. In this paper we introduce InferLine, a system which provisions and manages the individual stages of prediction pipelines to meet end-to-end tail latency constraints while minimizing cost. InferLine consists of a low-frequency combinatorial planner and a high-frequency auto-scaling tuner. The low-frequency planner leverages stage-wise profiling, discrete event simulation, and constrained combinatorial search to automatically select hardware type, replication, and batching parameters for each stage in the pipeline. The high-frequency tuner uses network calculus to auto-scale each stage to meet tail latency goals in response to changes in the query arrival process. We demonstrate that InferLine outperforms existing approaches by up to 7.6x in cost while achieving up to 34.5x lower latency SLO miss rate on realistic workloads and generalizes across state-of-the-art model serving frameworks.
Forward citations
Cited by 2 Pith papers
-
Action Chunk Scheduling for Batched Robot Policy Serving
A lookahead scheduler that simulates each robot's action-queue state before choosing batches improves throughput in heterogeneous multi-robot policy serving by up to 18% in real-world tests.
-
Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation
Cache-Craft reuses stored attention states for repeated RAG text chunks with selective recomputation, cutting redundant LLM prefill computation by 51% over prefix caching while retaining roughly 90% of answer quality.
Discussion (0). Continue with ORCID to comment.