REVIEW 10 cited by
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
M\'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity
read the original abstract
Large language models (LLMs) are increasingly integrated into many online services, yet they remain cost-prohibitive to deploy due to the requirement of expensive GPU instances. Prior work has addressed the high cost of LLM serving by improving the inference engine, but less attention has been given to selecting the most cost-efficient GPU type(s) for a specific LLM service. There is a large and growing landscape of GPU types and, within these options, higher cost does not always lead to increased performance. Instead, through a comprehensive investigation, we find that three key LLM service characteristics (request size, request rate, SLO) strongly influence GPU cost efficiency, and differing GPU types are most cost efficient for differing LLM service settings. As a result, the most cost-efficient allocation for a given service is typically a mix of heterogeneous GPU types. Based on this analysis, we introduce M\'elange, a GPU allocation framework that navigates these diverse LLM service characteristics and heterogeneous GPU option space to automatically and efficiently derive the minimal-cost GPU allocation for a given LLM service. We formulate the GPU allocation task as a cost-aware bin packing problem where GPUs are bins and items are slices of the service workload. Our formulation's constraints account for a service's unique characteristics, allowing M\'elange to be flexible to support diverse service settings and heterogeneity-aware to adapt the GPU allocation to a specific service. Compared to using only a single GPU type, M\'elange reduces deployment costs by up to 77% in conversational settings, 33% in document-based settings, and 51% in a mixed setting.
Forward citations
Cited by 10 Pith papers
-
Observation, Not Prediction: Conversation-Level Disaggregated Scheduling for Agentic Serving
Conversation-level scheduling in ConServe observes first-turn input length and KV occupancy to route prefill once and pin decoders, cutting p95 time-to-first-effective-token by 51% and improving energy efficiency by 7...
-
Specialize Roles, Mix Deployments: Pushing the Cost-Accuracy Frontier of LLM Agent Teams
AgentCARD benchmark shows heterogeneous LLM agent teams with mixed deployments reach the cost-accuracy frontier, delivering up to 44% higher accuracy or 12x lower cost than uniform teams, with domain-specific role bot...
-
Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs
Coral cuts multi-LLM serving costs by up to 2.79x and raises goodput by up to 2.39x on heterogeneous GPUs through adaptive joint optimization and a lossless two-stage decomposition that solves quickly.
-
PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving
PipeLive enables live pipeline parallelism reconfiguration for LLMs via KV cache redesign and VM-migration-inspired patching, cutting TTFT by 2.5x and reconfiguration time to under 10ms.
-
Efficient Remote KV Cache Reuse with GPU-native Video Codec
KVCodec uses GPU-native video codecs and pipelined fetching to compress and transmit KV caches, delivering up to 3.51x faster TTFT than prior methods while preserving accuracy.
-
Beyond Per-Token Pricing: A Concurrency-Aware Methodology for LLM Infrastructure Cost Estimation
Effective LLM inference cost per million output tokens varies 2.5-36x with offered request rate due to utilization, addressed by a concurrency-aware measurement methodology and open-source vLLM tool validated across m...
-
Idleness is Relative: Exploiting Tool-Call Idle Windows for Offloading in Agentic Systems with MORI
MORI improves throughput 20-71% and TTFT 18-43% over baselines by ranking programs on a continuous idleness spectrum and shifting the GPU-CPU boundary to match capacity in agentic LLM serving.
-
C2CServe: Leveraging NVLink-C2C for Elastic Serverless LLM Serving on MIG
C2CServe is a request-granularity serverless LLM serving system that keeps weights in host memory and streams them via C2C to MIG instances, cutting cold-start latency up to 7.1x while preserving TTFT/TPOT under contention.
-
The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project
The Workload-Router-Pool architecture is a 3D framework for LLM inference optimization that synthesizes prior vLLM work into a 3x3 interaction matrix and proposes 21 research directions at the intersections.
-
GoodServe: Towards High-Goodput Serving of Agentic LLM Inferences over Heterogeneous Resources
GoodServe proposes a predict-and-rectify routing system for agentic LLM inferences on heterogeneous GPUs that improves goodput by up to 27.4%.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.