chitu

RuntimesPythonApache-2.0★ 3.0k
GitHub ↗

Chitu is a production-grade LLM inference framework supporting NVIDIA, Ascend, Muxi, Hygon and other chips, from single GPU to large cluster deployments

Runtime
Runs
LLM inference and serving
Hardware
NVIDIA GPUs, Huawei Ascend 910B, Muxi, Hygon, Moore Threads, CPU
API
OpenAI-compatible serving

Agent stacks with this tool(2)View graph