20 results for βBatchingβ
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.β
Want pure semantic search? Try claim verification β
This paper introduces Online Dynamic Batching (ODB), a drop-in system that improves the efficiency of large language model (LLM) training.
Weifang Zhang, Yuzhou Nie, Bowen Pang, Guangrui Ma +1 more
This paper proposes a hybrid scheduler that dynamically switches between exclusive batching and mixed batching for LLM inference, achieving superior throughput, especially on bandwidth-constrained GPUβ¦
KatoANN is a CPU ANN search system that removes the tradeoff between throughput and recall by batching distance scans on Intel AMX.
This paper studies capacitated line aggregation with per-batch maximum delay and presents several algorithms with competitive ratios.
This paper investigates the use of strategically diverse data in self-training for LLMs, showing that diversity of approaches can matter more than correctness or teacher scale.
One clear sentence describing what this paper does
Cheng-Han Huang, Yongliang Sun, Chaoyan Huang, Ismail Alkhouri +1 more
The paper establishes conditions for QUBO formulations of combinatorial optimization problems that guarantee valid binary and feasible local minimizers using gradient-based methods.
Hanna Foerster, Ilia Shumailov, Cheng Zhang, Yiren Zhao +2 more
This paper identifies a critical privacy vulnerability, termed Quantamination, where dynamic quantization in popular ML frameworks can leak sensitive user data across batch boundaries.
This paper introduces a mechanistic neuronal network model for multilayer learning, offering biological insights and an alternative to backpropagation.
A simple online algorithm is presented for the stacking problem to avoid shifts with a sufficient condition involving stacking area dimension, load/unload points, and maximum items.
This paper proposes a dependency-aware autoscaling framework for serverless computing, integrating graph-based bottleneck identification, short-term workload forecasting, multi-model consensus, and coβ¦
The paper proposes an architecture for sequential statistical procedures that can be used in various applications.
This paper investigates the impact of batch sampling strategies using text and audio embeddings on text-to-music generation under low-data conditions.
Weinan Liu, Zeyuan Ding, Dian Ding, Chengcheng Wan +4 more
This paper presents SliceScheduler, a dynamic operator-level scheduling system for multi-tenant model serving that improves GPU utilization and maintains SLA.