RadixArk发布开源强化学习框架Miles v0.1
RadixArk开源了Miles v0.1框架,帮你调试RL训练,提高硬件效率,已在多个前沿模型上验证。
RadixArk公司发布了Miles v0.1,这是一个开源的强化学习框架,专门用于训练LLM和多模态模型。
该框架已在过去9个月内有72名贡献者提交了1,326次代码提交,并进行了85个GPU端到端CI测试。Miles已在Kimi K3、DeepSeek V4、Qwen 3.
8、GLM 5.2等前沿开源模型上进行了实战测试。
目前已有包括humansand、periodiclabs等多家公司在NVIDIA和AMD硬件上使用Miles进行前沿模型开发和生产强化学习工作负载。
Important contribution! 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 contributors have landed 1,326 commits, 85 GPU E2E CI tests, battle-testing Miles on frontier open models like Kimi K3, DeepSeek V4, Qwen 3.8, GLM 5.2, Inkling, MiniMax H3, etc. Miles powers frontier-model development and production RL workloads at @humansand , @periodiclabs , @modal , @DecagonAI , @Eigent_AI , @nebiusai , @IBM and more, on both @NVIDIAAI and @AIatAMD hardware. Here is what we built, and why teams picked Miles🧵
This report is categorized under AITOP's "Products" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Miles, RadixArk, DeepSeek, Qwen.
Source attribution: curated from Aravind Srinivas (@AravSrinivas). Cross-source corroboration: 6 independent sources have covered this development (including ollama, AWS Machine Learning Blog, OpenAI Blog), confirming industry-wide signal strength.