SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs. Zero-config multi-GPU: measures PCIe bandwidth, places attention and hot experts where they fit.
Derived from this repo's Cargo dependencies and activity — difficulty is an estimate from codebase size and scope.
Matched by dependency overlap in Cargo manifests — each card notes the most distinctive crates both projects share.
SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs. Zero-config multi-GPU: measures PCIe bandwidth, places attention and hot experts where they fit.
Virtio socket support for Rust
SochDB is a high-performance embedded, ACID-compliant vector database purpose-built for AI agents and memory
A container debugging tool based on FUSE
Rust interface to the Linux GPIO Character Device API (/dev/gpiochip...)
Rust library providing access to spidev devices under Linux
Enables streaming of images to and from CRIU during checkpoint/restore with low overhead
An adaptive-radix-tree metadata storage engine
An io_uring backed runtime for Rust