Deq core
High-performance quantized GEMV kernels for CPU-only LLM inference. Direct dot product on Q8_0/Q6_K/Q4_K GGUF blocks with AVX2+FMA SIMD — 3.0x decode speedup.
A Tokio async, sharded SPSC/MPSC/MPMC ring buffer in Rust.
Core tensor and autograd engine for ferrotorch — PyTorch in Rust
An async, lock-free, sharded, cache-aware SPSC/MPSC/MPMC ring buffer in Rust.
A highly parallel Perl 5 interpreter written in Rust