Jha, Siddharth

2 publications

ICMLW 2024 Characterizing Prompt Compression Methods for Long Context Inference Siddharth Jha, Lutfi Eren Erdogan, Sehoon Kim, Kurt Keutzer, Amir Gholami

ICMLW 2024 Learned Best-Effort LLM Serving Siddharth Jha, Coleman Richard Charles Hooper, Xiaoxuan Liu, Sehoon Kim, Kurt Keutzer