4 citations · 5 across the 10 of their papers we have counts for
Showing 2025Show all
2 papers · 1 filter
cs.LG2025
CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Rounding
Ziteng Sun, Adrian Benton, Samuel Kushnir +4
Post-training quantization is an effective method for reducing the serving cost of large language models, where the standard approach is to use a round-to-nearest quantization leve…
cs.AI2025
: Faster Test-Time Scaling through Speculative Drafts
Mert Cemri, Nived Rajaraman, Rishabh Tiwari +6
Scaling test-time compute has driven the recent advances in the reasoning capabilities of large language models (LLMs), typically by allocating additional computation for more thor…