A differentiable NAS framework jointly optimizes LLM architecture and mixed-precision quantization for linear layers, yielding up to 1.4x faster inference or 6% higher accuracy than sequential baselines on reasoning tasks.
arXiv preprint arXiv:2402.04902 (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LLM Compression with Jointly Optimizing Architectural and Quantization choices
A differentiable NAS framework jointly optimizes LLM architecture and mixed-precision quantization for linear layers, yielding up to 1.4x faster inference or 6% higher accuracy than sequential baselines on reasoning tasks.