Modal uses Miles from RadixArk as its RL framework, with SGLang samplers and a Megatron-LM trainer that updates the policy in BF16 on B200 GPUs. It runs two setups: mixed samplers spanning six accelerator types and three precisions (BF16, FP8 and NVFP4), and homogeneous samplers that run only on B200s with BF16 weights and a BF16 KV cache.
Part of a thread · earlier post
We use Miles from @radixark as the RL framework, with @sgl_project samplers and a Megatron-LM trainer that updates the policy in BF16 on B200 GPUs. There are two setups:
1. Mixed samplers that span six kinds of accelerators and three precisions (BF16, FP8 and NVFP4).
2. Homogeneous samplers that run only on B200s with BF16 weights and a BF16 KV cache.
Source: Modal · x.comPublished · added here
