Approximate Speculative Decoding
Paper • 2608.03447 • Published • 1
Yuannuo Feng
ynFeng
·
AI & ML interests
PhD student @ Beihang University. Efficient LLM inference, compute-in-memory.
Recent Activity
authored a paper 6 days ago
ASSERT: Adaptive Stochastic Sampling for Robust Diffusion Models on Analog Compute-in-Memory Hardware authored a paper 6 days ago
Selective KV Cache Protection for Noise-Resilient LLM Inference on Analog Compute-In-Memory Systems authored a paper 6 days ago
ROMER: Expert Replacement and Router Calibration for Robust MoE LLMs on Analog Compute-in-Memory SystemsOrganizations
upvoted a paper 6 days ago