qMLX: Custom inference engine for Qwen 3.5 122B on Apple Silicon, extending MLX with hybrid attention support, SSD-backed KV cache, and RYS layer duplication for efficient large-model serving on consumer hardware.

Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference

HelixLM - a recurrent heterogeneous graph neural LLM combining biological neural column random wiring, hybrid attention, and Mamba-2 for hyperpersonalized and on-device AI.

Rust/Python KV-cache block manager for MLA and hybrid-attention LLM serving, with content-addressed sharing, per-layer layouts, FP4/FP8 accounting, and distributed cache semantics.