High-speed Large Language Model Serving for Local Deployment

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

A collection of modern C++ libraries, include coro_http, coro_rpc, compile-time reflection, struct_pack, struct_json, struct_xml, struct_pb, easylog, async_simple etc.

Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training

library to read/write .npy and .npz files in C/C++

100 Gbps TCP/IP stack for Vitis shells

TAPA compiles task-parallel HLS program into high-performance FPGA accelerators.

High-Performance Sparse Linear Algebra on HBM-Equipped FPGAs Using HLS

FlexFlow Serve: Low-Latency, High-Performance LLM Serving

A graph linear algebra overlay