Skip to content

AReaL-MinT

AReaL-MinT is an open-source, self-hosted MinT training runtime built on AReaL (FSDP2 training) and SGLang (inference). It exposes the same HTTP API as MinT, so the same SDK script runs unchanged against a local deployment.

Under the hood, a FastAPI control plane dispatches each request to its backend: training to AReaL's FSDP2 engine, inference to SGLang with LoRA hot-reload. Every write returns a future the client polls.

MinT exposes a Tinker-compatible client surface β€” see the Tinker-compatible API reference for the shared types and clients.

Algorithms

Algorithm Status Notes
SFT Available LoRA SFT, checkpoint save/load, resume, sampler handoff
GRPO Available Group Relative Policy Optimization; group-relative advantages without a value critic

Supported models

Family Size GPU layout
Qwen3.6 27B (Dense) 4 FSDP actor + 4 SGLang rollout
Qwen3.6 35B-A3B (MoE) 4 FSDP actor + 4 SGLang rollout

Quick start

For prerequisites, install steps, and the architecture overview, see the AReaL-MinT repository.