Search

Bei Yu

CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference
PreMoe: Lightening MoEs on Constrained Memory by Expert Pruning and Retrieval
Betterv: Controlled verilog generation with discriminative guidance
DiffSAT: Differential MaxSAT Layer for SAT Solving
FuseGPT: Learnable Layers Fusion of Generative Pre-trained Transformers
Layout decomposition via boolean satisfiability
Neuroselect: Learning to select clauses in sat solvers
Parallel gröbner basis rewriting and memory optimization for efficient multiplier verification

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.