DSpark and DFlash2 draft models for faster inference with speculative decoding
Yosef Worku Alemneh
rasyosef
AI & ML interests
Pretraining, Supervised Fine Tuning, Direct Preference Optimization, Retrieval Augmented Generation (RAG), Function Calling
Recent Activity
new activity about 12 hours ago
IFM/K2-Horizon-7B-Uno:Independent throughput benchmark on RTX PRO 6000 (Blackwell): Uno vs DSpark at batch 1 and 64 new activity about 14 hours ago
IFM/K2-Horizon-7B:⚡ Up to 5.1x faster inference with DSpark speculative decoding (71 --> 364 tokens/sec)