Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
PELM: Power Efficient On-Device LLM Inference with Speculative Decoding and Dynamic Voltage Frequency Scaling
Weisi Yang, Stephen Xia
Deploying Large Language Models (LLMs) directly on mobile platforms at the edge is gaining traction due to a myriad of benefits, such as increased privacy, personalization, and red…
cs.LG2026
Depth Exploration for LLM Decoding
Weisi Yang, Zipeng Sun, Stephen Xia
Autoregressive LLM decoding evaluates every generated token through the full layer stack, even though many tokens become predictable at intermediate depths. Existing lossless depth…
cs.LG2025
MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs
Hongjun Xu, Junxi Xia, Weisi Yang +2
Deploying Mamba models on microcontrollers (MCUs) remains challenging due to limited memory, the lack of native operator support, and the absence of embedded-friendly toolchains. W…