conftrace_

gpu resource allocation

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

carbon efficiency (1) latency optimization (1) carbon emission (1) prefill-decoding disaggregation (1) large language model serving (1) throughput optimization (1) multi-objective optimization (1) time series forecasting (1) time series prediction (1) energy efficiency (1)

Papers

CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework NeurIPS 2024 DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving OSDI 2024