Showing 2025Show all
2 papers · 1 filter
cs.LG2025
FlexiQ: Adaptive Mixed-Precision Quantization for Latency/Accuracy Trade-Offs in Deep Neural Networks
Jaemin Kim, Hongjun Um, Sungkyun Kim +2
Neural networks commonly execute on hardware accelerators such as NPUs and GPUs for their size and computation overhead. These accelerators are costly and it is hard to scale their…
cs.CL2025
Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding
Sungkyun Kim, Jaemin Kim, Dogyung Yoon +3
LLMs have low GPU efficiency and high latency due to autoregressive decoding. Speculative decoding (SD) mitigates this using a small draft model to speculatively generate multiple…