DLS runs 1.5x-2.4x faster than tangermeme on A100, verified within numerical precision
anshulkundaje · x · 2026-11-12
A technical benchmark note: on an A100, DLS runs 1.5x faster in FP32 and 2.4x faster in TF32 compared to tangermeme's implementation. Both the scoring and DLS optimizations were verified to be within numerical precision of the naive/general implementations, so the speedup doesn't come at the cost of correctness. Useful reference for anyone running saliency analysis pipelines.
More from Research
- Token pooling combines well with embedding quantization and Matryoshka — antoine_chaffin · 2026-11-12
- FAME: exploration planning method transfers across scenes, beating NBP by 6.6 points on reconstruction — jiqizhixin · 2026-11-12
- E11 Bio hiring computational scientist for petabyte imaging and agentic AI labs — anderssandberg · 2026-11-12
- EPFL: Claude writes EEG network weights by reasoning, matching gradient training with 6x fewer subjects — epfl-ch · 2026-11-12
- Differentiable SSSS framework brings single-image real-time skin digitization to game engines — ssh4net · 2026-11-12
- NeurIPS paper proves when RNN+MLP can provably recover true robot state — chriswolfvision · 2026-11-12