@sgl_project: SGLang is proud to be the native rollout engine for Miles. We're here to keep the tokens flowing and the GPUs busy Grea…
Summary
SGLang is announced as the native rollout engine for Miles v0.1, an open-source reinforcement learning framework for LLMs and multimodal models, aimed at improving throughput, cache efficiency, and stability in RL training at scale.
View Cached Full Text
Cached at: 08/18/26, 06:32 PM
SGLang is proud to be the native rollout engine for Miles. We’re here to keep the tokens flowing and the GPUs busy
Great to see more and more teams using SGLang for post-training rollout. We’ll keep pushing on throughput, cache efficiency, and day-0 model coverage, so RL runs stay fast and stable at any scale
RadixArk (@radixark): Today we’re launching Miles v0.1, an open-source RL framework for LLMs and multimodal models.
RL training is easy to start and hard to debug. Miles helps you ensure your run is correct, use hardware efficiently, and keep RL running at scale.
Over the past 9 months, 72
Similar Articles
@MiniMax_AI: Congrats to our long-term partner SGLang/RadixArk on the launch of Miles v0.1! From M-Series to H3 and Music 3, we’ve b…
RadixArk launches Miles v0.1, an open-source reinforcement learning framework for large language models and multimodal models, aimed at simplifying and scaling RL training.
Miles v0.1: Production-level Post-training (20 minute read)
Miles v0.1 is a production-ready system for frontier post-training, optimizing reinforcement learning loops with fully asynchronous RL and agentic rollouts via SGLang.
Miles: A PyTorch-Native Stack for Large-Scale LLM RL Post-Training (14 minute read)
Miles is an open-source PyTorch-native framework from RadixArk for large-scale LLM reinforcement learning post-training, integrating SGLang, Megatron-LM, and Ray for high-throughput rollout and distributed training.
@PyTorch: Built on PyTorch, Ray, SGLang, and NVIDIA Megatron-LM, Miles is an open source framework from RadixArk for large-scale …
Miles is an open source framework from RadixArk for large-scale LLM reinforcement learning post-training, integrating PyTorch, Ray, SGLang, and NVIDIA Megatron-LM with support for MoE, low-precision, and fault tolerance.
@modal: We worked with @lmsysorg and http://z-lab.ai to - integrate DFlash spec into @sgl_project - make it faster with overlap…
Modal collaborated with LMSys and Z Lab to integrate DFlash speculative decoding into SGLang, achieving up to 4.3x throughput improvement over baseline and 1.5x over native multi-token prediction for large language models.