71 citations · 253 across the 31 of their papers we have counts for
5 papers · 1 filter
Measuring and Reducing Cross-Vendor Mismatch in Language Models
Erland Hilman Fuadi, Chong Tian, Xiaosong Ma +1
Running the same language model on different graphics processing unit (GPU) vendors can produce different logits, even when the model weights and inputs are the same. We analyze cr…
DeltaServe: Host-Agnostic Co-Serving of Inference and Fine-Tuning for LLMs
Jiaxuan Chen, Jianshu She, Ye Yuan +5
LLM serving systems are provisioned for peak load to meet strict latency targets, leaving substantial GPU compute idle whenever traffic falls below peak. We present DeltaServe, a h…
COPUS: Co-adaptive Parallelism and Batch Size Selection in Large Language Model Training
Akhmed Sakip, Erland Hilman Fuadi, Omar Sayedelahl +6
Training large language models requires jointly configuring two interdependent aspects of the system: the global batch size, which governs statistical efficiency, and the 3D parall…
Exposing Cross-Modal Consistency for Fake News Detection in Short-Form Videos
Chong Tian, Yu Wang, Chenxu Yang +5
Short-form video platforms are major channels for news but also fertile ground for multimodal misinformation where each modality appears plausible alone yet cross-modal relationshi…
LAPS: A Length-Aware-Prefill LLM Serving System
Jianshu She, Zonghang Li, Hongchao Du +7
LAPS identifies and disaggregates requests with different prompt lengths in LLM serving to reduce TTFT latency. While recent systems have decoupled the prefill and decode stages to…