Ekka: Automated Diagnosis of Silent Errors in LLM Inference
cs.DC, cs.AI, cs.SE
Submitted: 2026-06-03
Updated: 2026-11-03
Code: https://github.com/anthropics/claude-code
Terminology
Sources
- Bayesian Online Changepoint Detection
- Bridging Bug Localization and Issue Fixing: A Hierarchical Localization Framework Leveraging Large Language Models
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- Measuring Massive Multitask Language Understanding
- TTrace: Lightweight Error Checking and Diagnosis for Distributed Training
- Gemma 3 Technical Report
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- HuggingFace's Transformers: State-of-the-art Natural Language Processing
- Towards Understanding Bugs in Distributed Training and Inference Frameworks for Large Language Models
- OrcaLoca: An LLM Agent Framework for Software Issue Localization
- HellaSwag: Can a Machine Really Finish Your Sentence?
Related papers
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
- Seamless Reconfiguration for DAG-BFT (Technical Report)
- ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends
- AgentWeave: Efficient Distributed Agent Serving via Flow Decomposition