An empirical pipeline combining standard quantization and pruning on LLMs for root-cause and response tasks in network fault tickets claims simultaneous energy reduction and performance gains on two datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.PF 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Energy-Aware LLMs: A step towards sustainable AI for downstream applications
An empirical pipeline combining standard quantization and pruning on LLMs for root-cause and response tasks in network fault tickets claims simultaneous energy reduction and performance gains on two datasets.