[KongchangAI]
Person

Tao Lin

An engineer at RadixArk responsible for the development and practical application of Miles, an open-source reinforcement learning training framework, with a focus on asynchronous RL and sandbox isolation.

Timeline (last 90 days)

Oct 26

The open-source training framework Miles supports scaling from a single GPU to hundreds of GPUs, is compatible with NVIDIA and AMD hardware, and provides day-one support for mainstream open-source models.

Unverified50%

All Facts (1)

Unverified

The open-source training framework Miles supports scaling from a single GPU to hundreds of GPUs, is compatible with NVIDIA and AMD hardware, and provides day-one support for mainstream open-source models.

50%

Source Articles

AI Agent Training in Practice: From Environment Setup to ScalingOct 26