Get started
Author

Hai Li

Institution: Duke University
Observed institution: Duke University
ORCID: 0000-0003-3228-6544
Observed ORCID: 0000-0003-3228-6544
OpenAlex ID: A5144330022
EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture
2026 · Bowen Duan, Cong Guo, et al. · Proceedings - International Symposium on Computer Architecture/Proceedings
OASIS: Outlier-Aware LUT-Based GEMM with Dual-Side Quantization for LLM Inference Acceleration
2026 · Xueying Wu, Baijun Zhou, et al. · Proceedings - International Symposium on Computer Architecture/Proceedings
PDF
DirectGeMM: Eliminating the GeMV Bottleneck in Analog In-Memory Computing
2026 · Tomohisa Kawakami, Tergel Molom-Ochir, et al. · IEEE International Symposium on Circuits and Systems proceedings
CAMformer: Binary Associative Memory Is All You Need
2026 · Tergel Molom-Ochir, Benjamin F. Morris, et al. · IEEE Transactions on Circuits and Systems I Regular Papers
Works count: 4
Citation count:
H-index:
I10-index:
Year
Topic
Type