Full Text Available
Access Full Text at Repository
Search Results - "ArXiv cs.DC Recent Papers"
Search alternatives:
- papers »
-
CCL-Bench 1.0: A Trace-Based Benchmark for LLM Infrastructure
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
Online Article RSS Article -
ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
ADELIA: Automatic Differentiation for Efficient Laplace Inference Approximations
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
ResiHP: Taming LLM Training Failures with Dynamic Hybrid
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
Safactory: A Scalable Agent Factory for Trustworthy Autonomous Intelligence
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
TACO: A Toolsuite for the Verification of Threshold Automata
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
FalconGEMM: Surpassing Hardware Peaks with Lower-Complexity Matrix Multiplication
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
Relay Buffer Independent Communication over Pooled HBM for Efficient MoE Inference on Ascend
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
MoE-Hub: Taming Software Complexity for Seamless MoE Overlap with Hardware-Accelerated Communication on Multi-GPU Systems
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
SuperPaymaster: Eliminating Centralized Signer Authority via Asset-Oriented Abstraction to Reconcile Usability and Decentralization in Account Abstraction
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
A Privacy-Preserving Machine Learning Framework for Edge Intelligence: An Empirical Analysis
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
LLM-Enhanced Deep Reinforcement Learning for Task Offloading in Collaborative Edge Computing
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
Irminsul: MLA-Native Position-Independent Caching for Agentic LLM Serving
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
Towards Compute-Aware In-Switch Computing for LLMs Tensor-Parallelism on Multi-GPU Systems
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
Accelerating MoE with Dynamic In-Switch Computing on Multi-GPUs
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
A Scalable Digital Twin Framework for Energy Optimization in Data Centers
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text
-
EdgeServing: Deadline-Aware Multi-DNN Serving at the Edge
Published in ArXiv cs.DC Recent Papers (2026)Subjects: “…ArXiv cs.DC Recent Papers…”
Get full text