From the 1 of 8 linked papers with an AI index.
8 papers
Approximate Speculative Decoding
Yuannuo Feng, Zegang Peng, Yuxin Xie +5
Speculative decoding accelerates autoregressive generation by verifying a draft block with a target model in parallel. Under standard greedy verification, decoding stops at the fir…
NANQ: Noise-Floor-Aware Mixed-Precision Non-Uniform Quantization for Analog Compute-in-Memory
Yizhe Chen, Wenshuai Yao, Saiya Wang +6
Analog compute-in-memory (CIM) enables energy-efficient neural network inference, but device variation and read noise can severely degrade low-bit quantized models. Existing CIM-or…
Selective KV Cache Protection for Noise-Resilient LLM Inference on Analog Compute-In-Memory Systems
Yuannuo Feng, Wenyong Zhou, Yuang Ma +5
Analog compute-in-memory (CIM) arrays have emerged as a promising substrate for energy-efficient LLM inference, particularly for weight-stationary computations in linear layers. Ho…
Recall Before You Rank: Similarity-Guided Top- Reuse for Efficient Long-Context Attention
Wenshuai Yao, Wenyong Zhou, Hanyong Shao +5
The paper proposes ReTopK, a training‑free technique that speeds up dynamic top‑K sparse attention for long‑context language models by reusing supports from historically similar qu…
AB-Sparse: Sparse Attention with Adaptive Block Size for Accurate and Efficient Long-Context Inference
Di Liu, Ruitian Wang, Chen Chen +6
As large language models scale to longer contexts, loading the growing KV cache during attention computation becomes a critical bottleneck. Previous work has shown that attention c…
ROMER: Expert Replacement and Router Calibration for Robust MoE LLMs on Analog Compute-in-Memory Systems
Wenyong Zhou, Yuannuo Feng, Yizhe Chen +6
Large language models (LLMs) with mixture-of-experts (MoE) architectures achieve remarkable scalability by sparsely activating a subset of experts per token, yet their frequent exp…