High-performance C++23/Python sparse storage engine for PB-scale recommender system embeddings, Engram, MoE, and KV Cache. Features Hogwild! lock-free updates, slot-directory reads, AVX-512 SIMD, and Lance 2PC checkpointing. Jax, PyTorch are all available.
python machine-learning deep-learning cpp embeddings simd recsys recommender-system lock-free large-scale lance hogwild mixture-of-experts avx-512 cpp23 kv-cache engram sparse-attention large-language-models nanobind
-
Updated
Oct 20, 2026 - C++