EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization
Paper • 2502.02493 • Published
Yize Wu
EasyW
AI & ML interests
ML system, inference acceleration, distributed Infra
Recent Activity
authored a paper 1 day ago
EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU
Utilization authored a paper 1 day ago
Stable-LoRA: Stabilizing Feature Learning of Low-Rank AdaptationOrganizations
None yet
authored 2
papers 1 day ago