Cheaply Estimating Inference Efficiency Metrics for Autoregressive Transformer Models

Deepak Narayanan, Keshav Santhanam, Peter Henderson, Rishi Bommasani, Tony Lee +1 more
2/12/2026
DOISemantic Scholar

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Cite this paper

@article{narayanan2026cheaply,
  title  = {Cheaply Estimating Inference Efficiency Metrics for Autoregressive Transformer Models},
  author = {Deepak Narayanan and Keshav Santhanam and Peter Henderson and Rishi Bommasani and Tony Lee and Percy Liang},
  year   = {2026},
  doi    = {10.52202/075280-2904},
  url    = {https://doi.org/10.52202/075280-2904},
  journal = {NEURIPS 2023 2023}
}

Discussion