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.
A runtime for writing reliable asynchronous applications with Rust. Provides I/O, networking, scheduling, timers, ...
Enables streaming of images to and from CRIU during checkpoint/restore with low overhead
High Performance asynchronous, pure-Rust implementation of ZeroMQ messaging patterns, built upon Tokio. Includes io_uring and TCP Cork Support.
Common utilities used with hyper.
A thread-per-core async Rust runtime with IOCP/io_uring/polling.
Quilkin is a non-transparent UDP proxy specifically designed for use with large scale multiplayer dedicated game server deployments, to ensure security, access control, telemetry data, metrics and more.
HTTP benchmark client written in Rust, supporting HTTP/1.1, HTTP/2, and HTTP/3 (QUIC) with commandline mode and distributed mode.
A tokio-based modbus library
Jito Foundation MEV Solana Client