arXiv (All)
open access
PrismServe: Efficient LLM Serving on Heterogeneous Accelerator Clusters
Serving large language models across heterogeneous accelerators is challenging because partitioning a replica across device types introduces communication overhead during autoregressive decoding, while deploying complete quantized replicas can degrade model quality. We present PrismServe, a serving
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Self-Orchestrating Language Models: Leveraging Semantic Dependence for Efficient Inference#1084765
- Load Balancing with Evolving Workloads in Large-Scale Language Model Serving#1389174
- QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs#1144190
- Compute Has Shape: Self-Morphing the Internal Computation of Frozen LLMs#1489174
- OctoPipe: Reducing Pipeline Bubbles for Heterogeneous Models via Co-Optimizing Partitioning, Placement, and Scheduling#821727
Record · ID 1536019
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive