DeepInfer: High-performance, large-scale inference framework for DeepSeek models
The top stories in the fields you follow, at 06:00 your time.
Fast multi-modal decision model
Joint Subspace Sparse Attention for Efficient Long-Context Decoding
MixTok: Adaptive Visual Tokenization with Global 1D Tokens and Sparse 2D Refinement
Python repository · 1 stars
Rises show once there are 4 weeks of history (from mid-November).