A PyTorch native library for training speculative decoding models

One unified distributed system for high performance RPC, KV Cache, Message Queue, and File & Object Acceleration

MoocHelper is a High-performance MoonCake/Lua plugin, Language Server Protocol for MoonCake/Lua, on the shoulders of LuaHelper.

standard C library I/O FFI binding. 对C标准库中stdio的绑定

Instant setup scripts for cloud-based LLM development.

Discrete-event simulation of LLM request routing across multiple serving instances: round-robin, least-load, prefix-aware, and hybrid cache-aware routing with queue-depth threshold sweep.

Mooncake、vLLM、vLLM Ascend 相关的中文教程。

Self-contained PoC: cross-tenant timing oracle against shared content-hashed KV caches (Mooncake, Perplexity KV Messenger, DeepSeek 3FS).