5 papers
Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding
WenHung Lee, Jian-Jia Chen, Xiaolin Lin +6
While speculative decoding improves inference throughput for multi-batch long-context Large Language Models (LLMs), its efficiency is often limited by a verification bottleneck whe…
Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding
Pei-Shuo Wang, Jian-Jia Chen, Chun-Che Yang +4
The immense model sizes of large language models (LLMs) challenge deployment on memory-limited consumer GPUs. Although model compression and parameter offloading are common strateg…
Systolic Sparse Tensor Slices: FPGA Building Blocks for Sparse and Dense AI Acceleration
Endri Taka, Ning-Chi Huang, Chi-Chih Chang +3
FPGA architectures have recently been enhanced to meet the substantial computational demands of modern deep neural networks (DNNs). To this end, both FPGA vendors and academic rese…
V"Mean"ba: Visual State Space Models only need 1 hidden dimension
Tien-Yu Chi, Hung-Yueh Chiang, Chi-Chih Chang +2
Vision transformers dominate image processing tasks due to their superior performance. However, the quadratic complexity of self-attention limits the scalability of these systems a…
Palu: Compressing KV-Cache with Low-Rank Projection
Chi-Chih Chang, Wei-Cheng Lin, Chien-Yu Lin +7
Post-training KV-Cache compression methods typically either sample a subset of effectual tokens or quantize the data into lower numerical bit width. However, these methods cannot e…