Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
EAGLE-Pangu: Accelerator-Safe Tree Speculative Decoding on Ascend NPUs
Chang Han, Yijie Hu, Jingling Liu
Autoregressive decoding remains a primary bottleneck in large language model (LLM) serving, motivating speculative decoding methods that reduce expensive teacher-model invocations…
cs.LG2026
LeJOT-AutoML: LLM-Driven Feature Engineering for Job Execution Time Prediction in Databricks Cost Optimization
Lizhi Ma, Yi-Xiang Hu, Yihui Ren +2
Databricks job orchestration systems (e.g., LeJOT) reduce cloud costs by selecting low-priced compute configurations while meeting latency and dependency constraints. Accurate exec…