3 repos
lshAlgorithm/MoE-SpAc
Code for MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous…
9
2 commits
infinigence/SpecEE
Repo for SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting (ISCA25)
75
6 commits
dhishwasher/moe-offload-bench
Real on-hardware measurements of MoE expert-weight offloading on a 2-core/2.7GB-RAM box…
0