{"total":23,"rows":[{"id":"2509.16293","title":"Robust LLM Training Infrastructure at ByteDance","created":"2025-09-19","cited_by_count":16,"area":null},{"id":"2502.00075","title":"BTS: Harmonizing Specialized Experts into a Generalist LLM","created":"2025-01-31","cited_by_count":6,"area":null},{"id":"2509.03018","title":"Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training","created":"2025-09-03","cited_by_count":6,"area":null},{"id":"2503.11901","title":"Story of Two GPUs: Characterizing the Resilience of Hopper H100 and Ampere A100 GPUs","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2512.25059","title":"Reliable and Resilient Collective Communication Library for LLM Training and Serving","created":"2025-12-31","cited_by_count":4,"area":null},{"id":"2601.13655","title":"Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2412.12636","title":"TrainMover: An Interruption-Resilient Runtime for ML Training","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2510.21048","title":"xMem: A CPU-Based Approach for Accurate Estimation of GPU Memory in Deep Learning Training Workloads","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2605.17879","title":"Guard: Scalable Straggler Detection and Node Health Management for Large-Scale Training","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2504.06095","title":"Nonuniform-Tensor-Parallelism: Mitigating GPU failure impact for Scaled-up LLM Training","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2507.01880","title":"Evolving HPC services to enable ML workloads on HPE Cray EX","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2510.01256","title":"Kant: An Efficient Unified Scheduling System for Large-Scale AI Clusters","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2511.18323","title":"Crash-Consistent Checkpointing for AI Training on macOS/APFS","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2603.06630","title":"Photons = Tokens: The Physics of AI and the Economics of Knowledge","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2605.09370","title":"From Detection to Recovery: Operational Analysis on LLM Pre-training with 504 GPUs","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.11215","title":"ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Workload","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.23066","title":"Orbax: Distributed Checkpointing with JAX","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.24326","title":"ScaleAcross Explorer: Exploring Communication Optimization for Scale-Across AI Model Training","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.01680","title":"Don't Let a Few Network Failures Slow the Entire AllReduce","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.01409","title":"GPUAlert: A Zero-Instrumentation Process-Boundary Monitor for Diagnosing GPU Training-Job Failures","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.14614","title":"DumpsterCluster: From Dumpster Diving to Serving LLaMA-70B on $60 GPUs","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2610.00687","title":"Leto: Fast In-Place Recovery for LLM Training on Surviving Hardware","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03087","title":"Zephon: Elastic Determinism for Online, Stateful Foundation Model Data Loading Pipelines","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}