Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis Paper • 2412.01819 • Published 10 days ago • 29
ISTA-DASLab/Meta-Llama-3.1-70B-Instruct-AQLM-PV-2Bit-1x16 Text Generation • Updated Sep 17 • 2.77k • 45
SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices Paper • 2406.02532 • Published Jun 4 • 13