Pinned Loading

1. CARE-COVARIANCE-AWARE-AND-RANK-ENHANCED-DECOMPOSITION-FOR-ENABLING-MULTI-HEAD-LATENT-ATTENTION- CARE-COVARIANCE-AWARE-AND-RANK-ENHANCED-DECOMPOSITION-FOR-ENABLING-MULTI-HEAD-LATENT-ATTENTION- Public

   Forked from FutureMLS-Lab/CARE

   CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention

   Python

2. SpecForge SpecForge Public

   Forked from sgl-project/SpecForge

   Train speculative decoding models effortlessly and port them smoothly to SGLang serving.

   Python 1