> ## Documentation Index > Fetch the complete documentation index at: https://miles.radixark.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Advanced Features > Systems-level features for large-scale and long-running RL. This section covers the Miles features that the Core-features section of the homepage points at: low-precision training (FP8 / MXFP8 / NVFP4 / INT4 QAT), Rollout Routing Replay for MoE, fast weight updates over P2P RDMA, disaggregated RL rollout through an external service, fault tolerance, speculative decoding, and LoRA training and serving. Unified block-wise FP8, MXFP8, and NVFP4 recipes with matched training and rollout precision. W4A16 quantization-aware training for fitting large models on a single 8-GPU node. Capture expert routing during inference and replay during training. The mechanism that keeps MoE RL stable. Draft + target speculative rollout, with online MTP-SFT for the draft. Train a student on its own rollouts while matching teacher token probabilities through SGLang or Megatron teacher modes. Scale rollout across clusters and regions through an independent service, with versioned policy publication and request attribution. Train LoRA adapters with SFT or RL and serve them through SGLang from the same checkpoint.